@Inproceedings{ ChuangNB2013, title = {A Fixed-Based Flight Simulator Study: The Interdependence of Flight Control Performance and Gaze Efficiency}, year = {2013}, month = {7}, pages = {1-10}, abstract = {Here, a descriptive study is reported that addresses the relationship between flight control performance and instrument scanning behavior. This work was performed in a fixed-based flight simulator. It targets the ability of untrained novices to pilot a lightweight rotorcraft in a flight scenario that consisted of fundamental mission task elements such as speed and altitude changes. The results indicate that better control performance occurs when gaze is more selective for and focused on key instruments. Ideal instrument scanning behavior is proposed and its relevance for training instructions and visual instrument design is discussed.}, file_url = {fileadmin/user_upload/files/publications/2013/HCI-I-2013-Chuang.pdf}, web_url = {http://www.hcii2013.org/}, event_name = {15th International Conference on Human-Computer Interaction (HCI International 2013)}, event_place = {Las Vegas, NV, USA}, state = {accepted}, author = {Chuang LL{chuang}{Department Human Perception, Cognition and Action}, Nieuwenhuizen FM{fmnieuwenhuizen}{Department Human Perception, Cognition and Action} and B\"ulftoff HH{hhb}{Department Human Perception, Cognition and Action}} } @Inproceedings{ HerdtweckC2013, title = {Monocular Car Viewpoint Estimation with Circular Regression Forests}, year = {2013}, month = {6}, pages = {1-8}, web_url = {http://www.iv2013.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_name = {IEEE Intelligent Vehicles Symposium (IV 2013)}, event_place = {Gold Coast, Australia}, state = {accepted}, author = {Herdtweck C{grueschaan}{Department Human Perception, Cognition and Action} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Conference{ delaRosaSGBC2013, title = {Visual adaptation aftereffects to actions are modulated by high-level action interpretations}, year = {2013}, month = {5}, day = {11}, abstract = {Action recognition is critical for successful human interaction. Previous research highlighted the importance of the motor system to visual action recognition. Little is known about the visual tuning properties of processes involved in action recognition. Here we examined the visual tuning properties of processes involved in action recognition by means of a behavioral adaptation paradigm. Participants looked at an adaptor image (showing a person hitting or waving) for 4s and subsequently categorized a briefly presented test image as either hitting or waving. The test images were sampled from a video sequence showing a person moving from a hitting to a waving pose. We found the perception of the ambiguous test image to be significantly biased away from the adapted action (action adaptation aftereffect (AAA)). In subsequent experiments we investigated the origin of the AAA. The contrast inversion and mirror flipping of the adaptor image relative to the test images did not abolish the AAA suggesting that local contrastive sensitive units are not solely responsible for the AAA. Similarly the AAA was present when we chose adaptor images that were equated in terms of their emotional content indicating that the AAA is not merely mediated by units sensitive to the emotional content of an action. Moreover presenting words (e.g. "hitting" or "waving") instead of images as adaptors led to the disappearance of the AAA providing evidence that abstract high level linguistic cues about actions alone did not induce the AAA. Finally we changed the action interpretation of the adaptors leaving their physical properties unchanged by means of priming. We found that the priming of the action interpretation of the adaptors modulated the size of the AAA. Im summary these results suggest that mechanisms underlying action recognition are particularly sensitive to the high-level interpretation of an action.}, web_url = {http://www.visionsciences.org/abstract_detail.php?id=696}, event_name = {13th Annual Meeting of the Vision Sciences Society (VSS 2013)}, event_place = {Naples, FL, USA}, state = {published}, author = {de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}, Streuber S{stst}{Department Human Perception, Cognition and Action}, Giese M{giese}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Article{ BonevCE2012, title = {How do image complexity, task demands and looking biases influence human gaze behavior?}, journal = {Pattern Recognition Letters}, year = {2013}, month = {5}, volume = {34}, number = {7}, pages = {723–730}, abstract = {In this paper we propose an information-theoretic approach to understand eye-movement patterns, in relation to the task performed and image complexity. We commence with the analysis of the distributions and amplitudes of eye-movement saccades, performed across two different image-viewing tasks: free viewing and visual search. Our working hypothesis is that the complexity of image information and task demands should interact. This should be reflected in the Markovian pattern of short and long saccades. We compute high-order Markovian models of performing a large saccade after many short ones and also propose a novel method for quantifying image complexity. The analysis of the interaction between high-order Markovianity, task and image complexity supports our hypothesis.}, web_url = {http://www.sciencedirect.com/science/article/pii/S0167865512001687}, state = {published}, DOI = {10.1016/j.patrec.2012.05.007}, author = {Bonev B, Chuang LL{chuang}{Department Human Perception, Cognition and Action} and Escolano F} } @Article{ delaRosaB2013, title = {Motor-visual neurons and action recognition in social interactions. Commentary on Mirror neurons: From origin to function}, journal = {Behavioral and Brain Sciences}, year = {2013}, month = {5}, state = {accepted}, author = {de la Rosa S{delarosa}{Department Human Perception, Cognition and Action} and B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action}} } @Article{ PiryankovadKBM2013, title = {Egocentric distance perception in large screen immersive displays}, journal = {Displays}, year = {2013}, month = {4}, volume = {34}, number = {2}, pages = {153–164}, abstract = {Many scientists have demonstrated that compared to the real world egocentric distances in head-mounted display virtual environments are underestimated. However, distance perception in large screen immersive displays has received less attention. We investigate egocentric distance perception in a virtual office room projected using a semi-spherical, a Max Planck Institute CyberMotion Simulator cabin and a flat large screen immersive display. The goal of our research is to systematically investigate distance perception in large screen immersive displays with commonly used technical specifications. We specifically investigate the role of distance to the target, stereoscopic projection and motion parallax on distance perception. We use verbal reports and blind walking as response measures for the real world experiment. Due to the limited space in the three large screen immersive displays we use only verbal reports as the response measure for the experiments in the virtual environment. Our results show an overall underestimation of distance perception in the large screen immersive displays, while verbal estimates of distances are nearly veridical in the real world. We find that even when providing motion parallax and stereoscopic depth cues to the observer in the flat large screen immersive display, participants estimate the distances to be smaller than intended. Although stereo cues in the flat large screen immersive display do increase distance estimates for the nearest distance, the impact of the stereoscopic depth cues is not enough to result in veridical distance perception. Further, we demonstrate that the distance to the target significantly influences the percent error of verbal estimates in both the real and virtual world. The impact of the distance to the target on the distance judgments is the same in the real world and in two of the used large screen displays, namely, the MPI CyberMotion Simulator cabin and the flat displays. However, in the semi-spherical display we observe a significantly different influence of distance to the target on verbal estimates of egocentric distances. Finally, we discuss potential reasons for our results. Based on the findings from our research we give general suggestions that could serve as methods for improving the LSIDs in terms of the accuracy of depth perception and suggest methods to compensate for the underestimation of verbal distance estimates in large screen immersive displays.}, web_url = {http://www.sciencedirect.com/science/article/pii/S0141938213000036}, state = {published}, DOI = {10.1016/j.displa.2013.01.001}, author = {Piryankova IV{ivelina}{Department Human Perception, Cognition and Action}, de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}, Kloos U, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Mohler BJ{mohler}{Department Human Perception, Cognition and Action}} } @Article{ SonFLKBR2012, title = {Human-Centered Design and Evaluation of Haptic Cueing for Teleoperation of Multiple Mobile Robots}, journal = {IEEE Transactions on Cybernetics}, year = {2013}, month = {4}, volume = {43}, number = {2}, pages = {597-609}, abstract = {In this paper, we investigate the effect of haptic cueing on a human operator's performance in the field of bilateral teleoperation of multiple mobile robots, particularly multiple unmanned aerial vehicles (UAVs). Two aspects of human performance are deemed important in this area, namely, the maneuverability of mobile robots and the perceptual sensitivity of the remote environment. We introduce metrics that allow us to address these aspects in two psychophysical studies, which are reported here. Three fundamental haptic cue types were evaluated. The Force cue conveys information on the proximity of the commanded trajectory to obstacles in the remote environment. The Velocity cue represents the mismatch between the commanded and actual velocities of the UAVs and can implicitly provide a rich amount of information regarding the actual behavior of the UAVs. Finally, the Velocity+Force cue is a linear combination of the two. Our experimental results show that, while maneuverability is best supported by the Force cue feedback, perceptual sensitivity is best served by the Velocity cue feedback. In addition, we show that large gains in the haptic feedbacks do not always guarantee an enhancement in the teleoperator's performance.}, file_url = {fileadmin/user_upload/files/publications/2012/2013a-SonFraChuKimBueRob.pdf}, web_url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6294459}, state = {published}, DOI = {10.1109/TSMCB.2012.2212884}, author = {Son HI{chakurt}{Department Human Perception, Cognition and Action}, Franchi A{antonio}{Department Human Perception, Cognition and Action}, Chuang LL{chuang}{Department Human Perception, Cognition and Action}, Kim J{junsukkim}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Robuffo Giordano P{robu_pa}{Department Human Perception, Cognition and Action}} } @Conference{ Curio2013, title = {Novel Design Principles for Interfacing Artificial and Human Vision for Assistive Perceiving Systems}, year = {2013}, month = {3}, day = {4}, abstract = {Studying the interface between artificial and biological vision has been an area of research that has been greatly promoted for a long time. It seems promising that cognitive science can provide new ideas to interface computer vision and human perception, yet no established design principles do exist. In the first part of my talk I am going to introduce the novel concept of 'object detectability'. Object detectability refers to a measure of how likely a human observer is visually aware of the location and presence of specific object types in a complex, dynamic, urban scene. We have shown a proof of concept of how to maximize human observers' scene awareness in a dynamic driving context. Nonlinear functions are learnt from experimental samples of a combined feature vector of human gaze and visual features mapping to object detectabilities. We obtain object detectabilities through a detection experiment, simulating a proxy task of distracted real-world driving. In order to specifically enhance overall pedestrian detectability in a dynamic scene, the sum of individual detectability predictors defines a complex cost function that we seek to optimize with respect to human gaze. Results show significantly increased human scene awareness in hazardous test situations comparing optimized gaze and random fixation. Thus, our approach can potentially help a driver to save reaction time and resolve a risky maneuvre. In our framework, the remarkable ability of the human visual system to detect specific objects in the periphery has been implicitly characterized by our perceptual detectability task and has thus been taken into account. The framework may provide a foundation for future work to determine what kind of information a Computer Vision system should process reliably, e.g. certain pose or motion features, in order to optimally alert a driver in time-critical situations. Dynamic image data was taken from the Caltech Pedestrian database. I will conclude with a brief overview of recent work, including a new circular output random regression forest for continuous object viewpoint estimation and a novel learning-based, monocular odometry approach based on robust LVMs and sensorimotor learning, offering stable 3D information integration. Last but not least, I present results of a perception experiment to quantify emotion in estimated facial movement synergy components that can be exploited to control emotional content of 3D avatars in a perceptually meaningful way.}, event_name = {Max Planck Institute for Intelligent Systems: Perceiving Systems Department}, event_place = {Tübingen, Germany}, state = {published}, author = {Curio C{curio}{Department Human Perception, Cognition and Action}} } @Article{ delaRosaGBC2012, title = {The contribution of different cues of facial movement to the emotional facial expression adaptation aftereffect}, journal = {Journal of Vision}, year = {2013}, month = {1}, volume = {13}, number = {1:23}, pages = {1-15}, abstract = {Probing emotional facial expression recognition with the adaptation paradigm is one way to investigate the processes underlying emotional face recognition. Previous research suggests that these processes are tuned to dynamic facial information (facial movement). Here we examined the tuning of processes involved in the recognition of emotional facial expressions to different sources of facial movement information. Specifically we investigated the effect of the availability of rigid head movement and intrinsic facial movements (e.g., movement of facial features) on the size of the emotional facial expression adaptation effect. Using a three-dimensional (3D) morphable model that allowed the manipulation of the availability of each of the two factors (intrinsic facial movement, head movement) individually, we examined emotional facial expression adaptation with happy and disgusted faces. Our results show that intrinsic facial movement is necessary for the emergence of an emotional facial expression adaptation effect with dynamic adaptors. The presence of rigid head motion modulates the emotional facial expression adaptation effect only in the presence of intrinsic facial motion. In a second experiment we show these adaptation effects are difficult to explain by merely the perceived intensity and clarity (uniqueness) of the adaptor expressions. Together these results suggest that processes encoding facial expressions are differently tuned to different sources of facial movements.}, web_url = {http://www.journalofvision.org/content/13/1/23.full.pdf+html}, state = {published}, DOI = {10.1167/13.1.23}, author = {de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}, Giese MA{giese}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Article{ KrimmelKBBMDBR2013, title = {Three-Dimensional Assessment of Facial Development in Children With Unilateral Cleft Lip With and Without Alveolar Cleft}, journal = {Journal of Craniofacial Surgery}, year = {2013}, month = {1}, volume = {24}, number = {1}, pages = {313–316}, abstract = {Children with cleft lip or cleft lip and alveolus represent a minor group in the cleft population. The aim of this study was to analyze the faces of these children. In a prospective, cross-sectional study, 344 healthy children and 30 children with cleft lip or cleft lip and alveolus were scanned three-dimensionally at the age of 0 to 6 years. Twenty-one standard anthropometric landmarks were identified, and the images were superimposed. Growth curves for normal facial development were calculated. The facial morphology of cleft children was compared with that of unaffected children. Facial morphology and growth in the transverse direction of the examined patients appeared broadened in all levels. Especially the nasal landmarks indicated a widening of the nose. The landmarks ac l, sbal l, sbal r, c l, sn l, and ls l differed significantly from unaffected children. In the sagittal and vertical dimensions, there was no significant difference compared with unaffected children. Our study demonstrates that surgical and orthodontic treatment can restore the vertical and sagittal dimensions of the face in children with cleft lip with and without alveolar clefts; however, the transverse dimension—especially the nose—remains too broad.}, web_url = {http://journals.lww.com/jcraniofacialsurgery/pages/articleviewer.aspx?year=2013&issue=01000&article=00069&type=abstract}, state = {published}, DOI = {10.1097/SCS.0b013e318275ed60}, author = {Krimmel M, Kluba S, Breidt M{mbreidt}{Department Human Perception, Cognition and Action}, Bacher M, M\"uller-Hagedorn S, Dietz K, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Reinert s} } @Conference{ Curio2012_2, title = {Fusion of Human- and Machine-Vision: Research, Tools and Applications for Driving Assistance}, year = {2012}, month = {11}, day = {18}, event_name = {Bosch R&D}, event_place = {Hildesheim, Germany}, state = {published}, author = {Curio C{curio}{Department Human Perception, Cognition and Action}} } @Conference{ Chuang2012, title = {Active Information Retrieval in Scene Perception and Object Learning}, year = {2012}, month = {11}, day = {2}, abstract = {We pick out task-relevant information from the visual scene by moving our eyes and confidently manipulate our near-environment to achieve our goals. A better understanding of human behavior can be achieved by adopting this perspective. That is, humans are active (not passive observers). In my talk, I will address how we characterize natural information-seeking behavior in human participants in two context: a) scene processing, b) object learning. The first addresses how unrestrained gaze behavior can be characterized in terms of the information that is available in the scene. Here, I will explain why and how we eschew pure bottom-up procedures of using low-level image statistics to predict gaze movements. Next, I will discuss how we select which views of unfamiliar objects to learn, when we are free to manipulate them in 3D.}, event_name = {Department of Cognitive Neuroscience: Duke-NUS Graduate Medical School}, event_place = {Singapore}, state = {published}, author = {Chuang L{chuang}{Department Human Perception, Cognition and Action}} } @Conference{ NieuwenhuizenCB2012, title = {myCopter: Enabling Technologies for Personal Aerial Transportation Systems A progress report}, year = {2012}, month = {11}, abstract = {The volume of both road and air transportation continues to increase despite many concerns regarding its financial and environmental impact. The European Union ‘Out of the Box’ study suggests a personal aerial transportation system (PATS) as an alternative means of transport for daily commuting. The aim of the myCopter project is to determine the social and technical aspects needed to set up such a transportation system based on personal aerial vehicles (PAVs). The project focuses on three research areas: the human-machine interface and training, automation technologies, and social acceptance. In the first phase of the project, requirements were defined for automation technologies in terms of sensors and test platforms. Additionally, desirable features for PAVs were investigated to support the design and evaluation of technologies for an effective human-machine interface. Furthermore, an overview of the social-technological environment provided insight into the challenges and issues that surround the realisation of a PATS and its integration into the current transportation system in Europe. The presentation will elaborate on the second phase of the myCopter project, in which initial designs for a human-machine interface and training are developed. These are evaluated experimentally with a focus on aiding non-expert pilots in closed-loop control scenarios. Additionally, first evaluations of novel automation technologies are performed in simulated environments and evaluations on flying test platforms. At the same time, technological issues are evaluated that contribute towards a reflexive design of PAV technologies based on criteria that are acceptable to the general public. The presentation will also focus on the next stages of the project, in which further experimental evaluations will be performed on technologies for human-machine interfaces, and where developed automation technologies will be fully tested on unmanned flying vehicles. The expectations and perspectives of potential PAV user will be evaluated in group interviews in different European countries. Interesting technological and regulatory challenges need to be resolved for the development of a transportation system based on PAVs. The myCopter consortium combines the expertise from several research fields to tackle these challenges and to develop the technological and social aspects of a personal aerial transportation system.}, file_url = {fileadmin/user_upload/files/publications/2012/HELIWorld-2012-Nieuwenhuizen.pdf}, event_name = {4th International HELI World Conference at the International Aerospace Supply Fair AIRTEC 2012}, event_place = {Frankfurt a.M., Germany}, state = {published}, author = {Nieuwenhuizen F{fmnieuwenhuizen}{Department Human Perception, Cognition and Action}, Chuang L{chuang}{Department Human Perception, Cognition and Action} and B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action}} } @Conference{ Curio2012, title = {Fusing Human- and Machine-Vision for Enhanced Driver Perception and Decision Making}, year = {2012}, month = {10}, day = {12}, event_name = {Environment Perception Group, Daimler AG}, event_place = {Ulm, Germany}, state = {published}, author = {Curio C{curio}{Department Human Perception, Cognition and Action}} } @Article{ BiegBBC2012, title = {Looking for Discriminating Is Different from Looking for Looking's Sake}, journal = {PLoS ONE}, year = {2012}, month = {9}, volume = {7}, number = {9}, pages = {1-9}, abstract = {Recent studies provide evidence for task-specific influences on saccadic eye movements. For instance, saccades exhibit higher peak velocity when the task requires coordinating eye and hand movements. The current study shows that the need to process task-relevant visual information at the saccade endpoint can be, in itself, sufficient to cause such effects. In this study, participants performed a visual discrimination task which required a saccade for successful completion. We compared the characteristics of these task-related saccades to those of classical target-elicited saccades, which required participants to fixate a visual target without performing a discrimination task. The results show that task-related saccades are faster and initiated earlier than target-elicited saccades. Differences between both saccade types are also noted in their saccade reaction time distributions and their main sequences, i.e., the relationship between saccade velocity, duration, and amplitude.}, web_url = {http://www.plosone.org/article/fetchObjectAttachment.action;jsessionid=409E420397B230BE376365245B458D2A?uri=info%3Adoi%2F10.1371%2Fjournal.pone.0045445&representation=PDF}, state = {published}, DOI = {10.1371/journal.pone.0045445}, EPUB = {e45445}, author = {Bieg H-J{bieg}{Department Human Perception, Cognition and Action}, Bresciani J-P{bresciani}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Chuang LL{chuang}{Department Human Perception, Cognition and Action}} } @Article{ StreuberMBd2012, title = {The Influence of Visual Information on the Motor Control of Table Tennis Strokes}, journal = {Presence}, year = {2012}, month = {9}, volume = {21}, number = {3}, pages = {281-294}, abstract = {Theories of social interaction (i.e., common coding theory) suggest that visual information about the interaction partner is critical for successful interpersonal action coordination. Seeing the interaction partner allows an observer to understand and predict the interaction partner's behavior. However, it is unknown which of the many sources of visual information about an interaction partner (e.g., body, end effectors, and/or interaction objects) are used for action understanding and thus for the control of movements in response to observed actions. We used a novel immersive virtual environment to investigate this further. Specifically, we asked participants to perform table tennis strokes in response to table tennis balls stroked by a virtual table tennis player. We tested the effect of the visibility of the ball, the paddle, and the body of the virtual player on task performance and movement kinematics. Task performance was measured as the minimum distance between the center of the paddle and the center of the ball (radial error). Movement kinematics was measured as variability in the paddle speed of repeatedly executed table tennis strokes (stroke speed variability). We found that radial error was reduced when the ball was visible compared to invisible. However, seeing the body and/or the racket of the virtual players only reduced radial error when the ball was invisible. There was no influence of seeing the ball on stroke speed variability. However, we found that stroke speed variability was reduced when either the body or the paddle of the virtual player was visible. Importantly, the differences in stroke speed variability were largest in the moment when the virtual player hit the ball. This suggests that seeing the virtual player's body or paddle was important for preparing the stroke response. These results demonstrate for the first time that the online control of arm movements is coupled with visual body information about an opponent.}, web_url = {http://www.mitpressjournals.org/doi/abs/10.1162/PRES_a_00113}, state = {published}, DOI = {10.1162/PRES_a_00113}, author = {Streuber S{stst}{Department Human Perception, Cognition and Action}, Mohler BJ{mohler}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}} } @Inproceedings{ HerdtweckC2012_2, title = {Monocular Heading Estimation in Non-stationary Urban Environment}, year = {2012}, month = {9}, pages = {244-250}, abstract = {Estimating heading information reliably from visual cues only is an important goal in human navigation research as well as in application areas ranging from robotics to automotive safety. The focus of expansion (FoE) is deemed to be important for this task. Yet, dynamic and unstructured environments like urban areas still pose an algorithmic challenge. We extend a robust learning framework that operates on optical flow and has at center stage a continuous Latent Variable Model (LVM) [1]. It accounts for missing measurements, erroneous correspondences and independent outlier motion in the visual field of view. The approach bypasses classical camera calibration through learning stages, that only require monocular video footage and corresponding platform motion information. To estimate the FoE we present both a numerical method acting on inferred optical flow fields and regression mapping, e.g. Gaussian-Process regression. We also present results for mapping to velocity, yaw, and even pitch and roll. Performance is demonstrated for car data recorded in non-stationary, urban environments.}, note = {Best Conference Paper Award}, file_url = {fileadmin/user_upload/files/publications/2012/HerdtweckCurioMFI2012.pdf}, web_url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6343057}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_name = {IEEE International Conference on Multisensor Fusion and Information Integration (MFI 2012)}, event_place = {Hamburg, Germany}, state = {published}, ISBN = {978-1-4673-2511-0}, DOI = {10.1109/MFI.2012.6343057}, author = {Herdtweck C{grueschaan}{Department Human Perception, Cognition and Action} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Poster{ BiegBBC2012_2, title = {Asymmetries in saccadic latencies during interrupted ocular pursuit}, journal = {Perception}, year = {2012}, month = {9}, volume = {41}, number = {ECVP Abstract Supplement}, pages = {137}, abstract = {Smooth pursuit eye movements can be interrupted and resumed at a later stage, eg, when a concurrent task requires visual sampling from elsewhere. Here we address whether and how interruptive saccades are affected by pursuit movements. Our participants pursued an object which moved horizontally in a sinusoidal pattern (frequency: 0.25 Hz, amplitude: 4 deg. visual angle). During this, discrimination targets appeared at 10 deg. eccentricity, to the left or right of the center. They were timed so that they appeared for 1 second while the pursuit object moved either toward or away from the discrimination target's position. Saccade reaction times were earlier when the discrimination targets appeared in a position that the tracking object was moving towards. Interestingly, saccade RTs back to the pursuit object were shorter when the object moved away from the discrimination target. We conclude that interruptions of pursuit movements lead to asymmetries in saccade generation. These asymmetries could have been caused by biases in attention along the predicted pursuit path.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v120443}, event_name = {35th European Conference on Visual Perception}, event_place = {Alghero, Italy}, state = {published}, author = {Bieg H-J{bieg}{Department Human Perception, Cognition and Action}, Bresciani J-P{bresciani}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Chuang LL{chuang}{Department Human Perception, Cognition and Action}} } @Poster{ ChuangNB2012, title = {Eye-movement planning during flight maneuvers}, journal = {Perception}, year = {2012}, month = {9}, volume = {41}, number = {ECVP Abstract Supplement}, pages = {99}, abstract = {How are eye-movements planned to access relevant visual information during flight control? From the cockpit perspective, there are two classes of visual information that are relevant for flight control. First, the changing visuals of the external world provide direct perceptual feedback on how the pilot's command of the control stick is affecting the aircraft's current position, orientation and velocity. Second, flight instruments provide abstracted and specific values—on factors such as the aircraft's compass bearing and vertical speed—that have to be continuously monitored, in order for the global objective of certain maneuvers (eg, turns) to be achieved. Trained pilots have to coordinate their eye-movements across this structured visual workspace (ie, outside view and instruments) to access timely and task-relevant information. The current work focuses on providing descriptions of these planned eye-movements. Eye-movements were recorded of pilots in a high-fidelity flight simulator (100° field-of-view) whilst they performed specific flight maneuvers. Fixation durations and transitions between the individual instruments and aspects of the external environment are represented as network graphs. This allowed us to formally describe the sources of information that were relied on across the different tasks and to compare actual performance to expert predictions.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v120634}, event_name = {35th European Conference on Visual Perception}, event_place = {Alghero, Italy}, state = {published}, author = {Chuang L{chuang}{Department Human Perception, Cognition and Action}, Nieuwenhuizen F{fmnieuwenhuizen}{Department Human Perception, Cognition and Action} and B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action}} } @Poster{ KaulardSWBd2012, title = {Inverting natural facial expressions puzzles you}, journal = {Perception}, year = {2012}, month = {9}, volume = {41}, number = {ECVP Abstract Supplement}, pages = {103}, abstract = {The face inversion effect has often been demonstrated in face identification tasks. Less is known about whether processes underlying face expression recognition are also sensitive to face inversion. Face expression recognition is usually investigated using pictures of six emotional expressions. In everyday life, humans are however exposed to a much larger set of facial expressions, which are dynamic. Here, we examine the effect of face inversion on expression recognition for a variety of facial expressions displayed statically and dynamically. We measured participants'recognition accuracy for 12 expressions using a 13 alternative-forced-choice task. We varied the dynamics (videos versus pictures) and the orientation (upright versus inverted) of the presentation of the expressions in a completely crossed design. Accuracy was significantly higher when expressions were presented as videos (62%) than as pictures (47%). Similarly, recognition accuracy was significantly higher for upright (84%) compared to inverted (64%) expressions. Moreover, the effect of orientation changed significantly with expression type. No other effects were significant. This is the first study to report that face inversion affects the recognition of natural facial expressions. Because face inversion effects are interpreted as a sign of configural processing, our results suggest configural processing for a majority of facial expressions.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v120193}, event_name = {35th European Conference on Visual Perception}, event_place = {Alghero, Italy}, state = {published}, author = {Kaulard K{kascot}{Department Human Perception, Cognition and Action}, Schultz J{johannes}{Department Human Perception, Cognition and Action}, Wallraven C{walli}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}} } @Poster{ ChuangNB2012_2, title = {Investigating Gaze Behavior of Novice Pilots during Basic Flight Maneuvers}, year = {2012}, month = {9}, web_url = {http://research.fit.edu/hci-aero/hci-aero2012/Poster_Sessions.html}, event_name = {International Conference on Human-Computer Interaction in Aerospace (HCI-Aero 2012)}, event_place = {Bruxelles, Belgium}, state = {published}, author = {Chuang LL{chuang}{Department Human Perception, Cognition and Action}, Nieuwenhuizen FM{fmnieuwenhuizen}{Department Human Perception, Cognition and Action} and B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action}} } @Poster{ GieseCC2012, title = {Perceptual relevance of kinematic components of facial movements extracted by unsupervised learning}, journal = {Perception}, year = {2012}, month = {9}, volume = {41}, number = {ECVP Abstract Supplement}, pages = {150}, abstract = {The idea that complex facial or body movements are composed of simpler components (usually referred to as 'movement primitives'or 'action units') is common in motor control (Chiovetto 2011 Journal of Neurophysiology105(4), 1429-31.) as well as in the study of facial expressions (Ekman and Friesen, 1978). However, such components have rarely been extracted from real facial movement data. Methods: Combining a novel algorithm for anechoic demixing derived from (Omlor and Giese 2011 Journal of Machine Learning Research121111-1148) with a motion retargetting system for 3D facial animation (Curio et al, 2010, MIT Press, 47-65), we estimated spatially and temporally localized components that capture the major part of the variance of dynamic facial expressions. The estimated components were used to generate stimuli for a psychophysical experiment assessing classification rates and emotional expressiveness ratings for stimuli containing combinations of the extracted components. Results: We investigated how the information carried by the different extracted dynamic facial movement components is integrated in facial expression perception. In addition, we tried to apply different cue fusion models to account quantitatively for the obtained experimental results.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v120635}, event_name = {35th European Conference on Visual Perception}, event_place = {Alghero, Italy}, state = {published}, author = {Giese MA{giese}, Chiovetto E and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Poster{ delaRosaMBC2012, title = {View dependencies in the visual recognition of social interactions}, journal = {Perception}, year = {2012}, month = {9}, volume = {41}, number = {ECVP Abstract Supplement}, pages = {240}, abstract = {Humans daily physically interact with other people (eg when shaking hands). Understanding the action of others is important for a successful social interaction. Little is known about the visual processes underlying the visual recognition of social interactions. Here we were examined the view dependency of social interaction recognition. We used motion capture to record predefined interactions (eg high five; handshake; hug) acted out by pairs of participants and created 3D models of these interactions. In the actual experiment participants were presented with these interactions one at a time and had to identify a predefined interaction (1IFC task). We manipulated the view point (front, side, top, 45 degree side view) from which participants saw the interaction and the presentation time of the social interactions. We recorded participants'accuracy (as measured by d prime) and reaction time to identify a predefined social interaction. We found that the d primes and reaction time significantly depended on the view point of the social interaction. The results suggest the existence of view dependencies in the visual recognition of social interactions.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v120439}, event_name = {35th European Conference on Visual Perception}, event_place = {Alghero, Italy}, state = {published}, author = {de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}, Miekes S, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Conference{ SchultzFdBK2012, title = {How are facial expressions represented in the human brain?}, journal = {Perception}, year = {2012}, month = {9}, volume = {41}, number = {ECVP Abstract Supplement}, pages = {38}, abstract = {The dynamic facial expressions that we encounter every day can carry a myriad of social signals. What are the neural mechanisms allowing us to decode these signals? A useful basis for this decoding could be representations in which the facial expressions are set in relation to each other. Here, we compared the behavioral and neural representations of 12 facial expressions presented as pictures and videos. Behavioral representations of these expressions were computed based on the results of a semantic differential task. Neural representations of these expressions were obtained by multivariate pattern analysis of functional magnetic imaging data. The two kinds of representations were compared using correlations. For expression videos, the results show a significant correlation between the behavioral and neural representations in the superior temporal sulcus (STS), the fusiform face area, the occipital face area and the amygdala, all in the left hemisphere. For expression pictures, a significant correlation was found only in the left STS. These results suggest that of all tested regions, the left STS contains the neural representation of facial expressions that is closest to their behavioral representation. This confirms the predominant role of STS in coding changeable aspects of faces, which includes expressions.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v120194}, event_name = {35th European Conference on Visual Perception}, event_place = {Alghero, Italy}, state = {published}, author = {Schultz J{johannes}{Department Human Perception, Cognition and Action}, Fernandez Cruz AL{anafer}{Department Human Perception, Cognition and Action}, de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Kaulard K{kascot}{Department Human Perception, Cognition and Action}} } @Conference{ CurioGBd2012, title = {Motor-visual effects in the recognition of dynamic facial expressions}, journal = {Perception}, year = {2012}, month = {9}, volume = {41}, number = {ECVP Abstract Supplement}, pages = {44}, abstract = {Current theories on action understanding suggest a cross-talk between the motor and the visual system during the recognition of other persons'actions. We examined the effect of the motor execution on the visual recognition of dynamic emotional facial expressions using an adaptation paradigm. Previous research on facial expression adaptation has shown that the prolonged visual exposure to a static facial expression biases the percept of an ambiguous static facial expression away from the adapted facial expression. We used a dynamic 3D computational face model (Curio et al, 2010, MIT Press, 47-65) to examine motor-visual interactions in the recognition of happy and fearful facial expressions. During the adaptation phase participants (1) looked for a prolonged amount of time at a facial expression (visual adaptation); (2) executed repeatedly a facial expression (motor adaptation); (3) imagined the emotion corresponding to a facial expression (imagine adaptor). In the test phase participants always had to judge an ambiguous facial expression as either happy or fearful. We found an adaptation effect in the visual adaptation condition, and the reversed effect (priming effect) in the motor and imagine condition. Inconsistent with simple forms of motor resonance, this shows antagonistic influences of visual and motor adaptation.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v120450}, event_name = {35th European Conference on Visual Perception}, event_place = {Alghero, Italy}, state = {published}, author = {Curio C{curio}{Department Human Perception, Cognition and Action}, Giese M{giese}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}} } @Inproceedings{ BiegCFRB2012, title = {Einfluss von Ablenkung und Augenbewegungen auf Steuerungsaufgaben}, year = {2012}, month = {8}, pages = {341-344}, abstract = {In der vorliegenden Studie wurde der Einfluss visueller Ablenkung auf Steuerungsaufgaben untersucht. Die Ergebnisse deuten darauf hin, dass bereits eine kurze Verlagerung der Aufmerksamkeit und des Blicks mit einer systematischen Beeinflussung der Steuerungsaufgabe einhergeht. Im Gegenzug findet auch eine systematische Beeinflussung der Augenbewegungen durch die gleichzeitig durchgeführte Steuerungsaufgabe statt. Die Berücksichtigung solcher Interferenzen kann bei der Entwicklung von grafischen On-Board-Informationssystemen für Fahr- oder Flugzeuge von Nutzen sein.}, web_url = {http://dl.mensch-und-computer.de/handle/123456789/2907}, editor = {Reiterer, H. , O. Deussen}, publisher = {Oldenbourg}, address = {München, Germany}, booktitle = {Mensch & Computer 2012: 12. fachübergreifende Konferenz für interaktive und kooperative Medien}, event_name = {Mensch & Computer (M&C)}, event_place = {Konstanz, Germany}, state = {published}, ISBN = {978-3-486-71879-9}, author = {Bieg H-J{bieg}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Chuang LL{chuang}{Department Human Perception, Cognition and Action}} } @Poster{ DobsBCS2012, title = {Investigating factors influencing the perception of identity from facial motion}, journal = {Journal of Vision}, year = {2012}, month = {8}, volume = {12}, number = {9}, pages = {35}, abstract = {Previous research has shown that facial motion can convey information about identity in addition to facial form (e.g. Hill & Johnston, 2001). The present study aims at finding whether identity judgments vary depending on the kinds of facial movements and the task performed. To this end, we used a recent facial motion capture and animation system (Curio et al., 2006). We recorded different actors performing classic emotional facial movements (e.g. happy, sad) and non-emotional facial movements occurring in social interactions (e.g. greetings, farewell). Only non-rigid components of these facial movements were used to animate one single avatar head. In a between-subject design, four groups of participants performed identity judgments based on emotional or social facial movements in a same-different (SD) or a delayed matching-to-sample task (XAB). In the SD task, participants watched two distinct facial movements (e.g. happy and sad) and had to choose whether the same or different actors performed these facial movements. In the XAB task, participants saw one target facial movement X (e.g. happy) performed by one actor followed by two facial movements of another kind (e.g. sad) performed by two actors. Participants chose which of the latter facial movements was performed by the same actor as the one performing X. Prior to the experiment, participants were familiarized with the actors by watching them perform facial movements not subsequently tested. Participants were able to judge actor identities correctly in all conditions, except for the SD task performed on the emotional stimuli. Sensitivity to identity as measured by d-prime was higher in the XAB than in the SD task. Furthermore, performance was higher for social than for emotional stimuli. Our findings reveal an effect of task on identity judgments based on facial motion, and suggest that such judgments are easier when facial movements are less stereotypical.}, web_url = {http://www.journalofvision.org/content/12/9/35.abstract}, event_name = {12th Annual Meeting of the Vision Sciences Society (VSS 2012)}, event_place = {Naples, FL, USA}, state = {published}, author = {Dobs K{kdobs}{Department Human Perception, Cognition and Action}, B\"ulthoff I{isa}{Department Human Perception, Cognition and Action}, Curio C{curio}{Department Human Perception, Cognition and Action} and Schultz J{johannes}{Department Human Perception, Cognition and Action}} } @Article{ McDonnellBB2012, title = {Render me Real? Investigating the Effect of Render Style on the Perception of Animated Virtual Humans}, journal = {ACM Transactions on Graphics}, year = {2012}, month = {7}, volume = {31}, number = {4: SIGGRAPH 2012 Conference Proceedings}, pages = {91: 1-11}, abstract = {The realistic depiction of lifelike virtual humans has been the goal of many movie makers in the last decade. Recently, films such as Tron: Legacy and The Curious Case of Benjamin Button have produced highly realistic characters. In the real-time domain, there is also a need to deliver realistic virtual characters, with the increase in popularity of interactive drama video games (such as L.A. Noire™ or Heavy Rain™). There have been mixed reactions from audiences to lifelike characters used in movies and games, with some saying that the increased realism highlights subtle imperfections, which can be disturbing. Some developers opt for a stylized rendering (such as cartoon-shading) to avoid a negative reaction [Thompson 2004]. In this paper, we investigate some of the consequences of choosing realistic or stylized rendering in order to provide guidelines for developers for creating appealing virtual characters. We conducted a series of psychophysical experiments to determine whether render style affects how virtual humans are perceived. Motion capture with synchronized eye-tracked data was used throughout to animate custom-made virtual model replicas of the captured actors.}, web_url = {http://s2012.siggraph.org/attendees/sessions/100-71}, state = {published}, DOI = {10.1145/2185520.2185587}, author = {McDonnell R, Breidt M{mbreidt}{Department Human Perception, Cognition and Action} and B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action}} } @Conference{ Bieg2012, title = {Saccadic and pursuit eye movements during coordinated behaviors}, year = {2012}, month = {6}, day = {19}, abstract = {Gaze control is largely determined by an observer's behavioral goals. In this respect, eye movements are one of many coordinated actions to achieve these goals. In this presentation I will discuss experiments which studied the properties of saccadic and pursuit eye movements in concerted behaviors, for example in steering a vehicle. In this respect, I will consider an aspect of gaze control which has largely been neglected by previous research: the consequence of eye movements for visual perception and the associated behavioral consequence in terms of the value of the obtained additional information}, web_url = {http://webu2.upmf-grenoble.fr/LPNC/seminaire_2012-06-19_13h-14h}, event_name = {Laboratoire de Psychologie et Neurocognition (LPNC), Université Pierre Mendès-France}, event_place = {Grenoble, France}, state = {published}, author = {Bieg H-J{bieg}{Department Human Perception, Cognition and Action}} } @Article{ RedcayKS2012, title = {Look at this: the neural correlates of initiating and responding to bids for joint attention}, journal = {Frontiers in Human Neuroscience}, year = {2012}, month = {6}, volume = {6}, number = {169}, pages = {1-14}, abstract = {When engaging in joint attention, one person directs another person's attention to an object (Initiating Joint Attention, IJA), and the second person's attention follows (Responding to Joint Attention, RJA). As such, joint attention must occur within the context of a social interaction. This ability is critical to language and social development; yet the neural bases for this pivotal skill remain understudied. This paucity of research is likely due to the challenge in acquiring functional MRI data during a naturalistic, contingent social interaction. To examine the neural bases of both IJA and RJA we implemented a dual-video set-up that allowed for a face-to-face interaction between subject and experimenter via video during fMRI data collection. In each trial, participants either followed the experimenter's gaze to a target (RJA) or cued the experimenter to look at the target (IJA). A control condition, solo attention (SA), was included in which the subject shifted gaze to a target while the experimenter closed her eyes. Block and event-related analyses were conducted and revealed common and distinct regions for IJA and RJA. Distinct regions included the ventromedial prefrontal cortex for RJA and intraparietal sulcus and middle frontal gyrus for IJA (as compared to SA). Conjunction analyses revealed overlap in the dorsal medial prefrontal cortex (dMPFC) and right posterior superior temporal sulcus (pSTS) for IJA and RJA (as compared to SA) for the event analyses. Functional connectivity analyses during a resting baseline suggest joint attention processes recruit distinct but interacting networks, including social-cognitive, voluntary attention orienting, and visual networks. This novel experimental set-up allowed for the identification of the neural bases of joint attention during a real-time interaction and findings suggest that whether one is the initiator or responder, the dMPFC and right pSTS, are selectively recruited during periods of joint attention.}, web_url = {http://www.frontiersin.org/Human_Neuroscience/10.3389/fnhum.2012.00169/abstract}, state = {published}, DOI = {10.3389/fnhum.2012.00169}, author = {Redcay E, Kleiner M{kleinerm}{Department Human Perception, Cognition and Action} and Saxe R} } @Inproceedings{ EngelC2012, title = {Detectability prediction in dynamic scenes for enhanced environment perception}, year = {2012}, month = {6}, pages = {178-183}, abstract = {A driver assistance system realizes that the driver is distracted and that a potentially hazardous situation is emerging. Where should it guide the attention of the driver? Optimally to the spot that allows the driver to make the best decision. Pedestrian detectability has been proposed recently as a measure of the probability that a driver perceives pedestrians in an image [9]. Leveraging this information allows a driver assistance system to direct the attention of the driver to the spot that maximizes the probability that all pedestrians are seen. In this paper we extend this concept to dynamic scenes. We use an annotated video dataset recorded from a moving car in an urban environment and acquire the detectabilities of pedestrians via a psychophysical experiment. Based on these measured detectabilites we train a machine learning algorithm to predict detectabilities from a set of image features. We then exploit this mapping to predict the optimal focus of attention in a second experiment, thus demonstrating the usefulness of our method in a dynamic driver assistance context.}, file_url = {fileadmin/user_upload/files/publications/2012/IV2012-Engel.pdf}, web_url = {http://www.robesafe.es/iv2012/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_name = {IEEE Intelligent Vehicles Symposium (IV 2012)}, event_place = {Alcalá de Henares, Spain}, state = {published}, DOI = {10.1109/IVS.2012.6232267}, author = {Engel D{engel}{Department Human Perception, Cognition and Action} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Inproceedings{ HerdtweckC2012, title = {Experts of probabilistic flow subspaces for robust monocular odometry in urban areas}, year = {2012}, month = {6}, pages = {661-667}, abstract = {Visual odometry has been promoted as a fundamental component for intelligent vehicles. Relying solely on monocular image cues would be desirable. Nevertheless, this is a challenge especially in dynamically varying urban areas due to scale ambiguities, independent motions, and measurement noise. We propose to use probabilistic learning with auxiliar depth cues. Specifically, we developed an expert model that specializes monocular egomotion estimation units on typical scene structures, i.e. statistical variations of scene depth layouts. The framework adaptively selects the best fitting expert. For on-line estimation of egomotion, we adopted a probabilistic subspace flow estimation method. Learning in our framework consists of two components: 1) Partitioning of datasets of video and ground truth odometry data based on unsupervised clustering of dense stereo depth profiles and 2) training a cascade of subspace flow expert models. A probabilistic quality measure from the estimates of the experts provides a selection rule overall leading to improvements of egomotion estimation for long test sequences.}, file_url = {fileadmin/user_upload/files/publications/2012/IV-2012-Herdtweck-Curio.pdf}, web_url = {http://www.robesafe.es/iv2012/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_name = {IEEE Intelligent Vehicles Symposium (IV 2012)}, event_place = {Alcalá de Henares, Spain}, state = {published}, DOI = {10.1109/IVS.2012.6232238}, author = {Herdtweck C{grueschaan}{Department Human Perception, Cognition and Action} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Article{ ChuangVB2012_2, title = {Learned non-rigid object motion is a view-invariant cue to recognizing novel objects}, journal = {Frontiers in Computational Neuroscience}, year = {2012}, month = {5}, volume = {6}, number = {26}, pages = {1-8}, abstract = {There is evidence that observers use learned object motion to recognize objects. For instance, studies have shown that reversing the learned direction in which a rigid object rotated in depth impaired recognition accuracy. This motion reversal can be achieved by playing animation sequences of moving objects in reverse frame order. In the current study, we used this sequence-reversal manipulation to investigate whether observers encode the motion of dynamic objects in visual memory, and whether such dynamic representations are encoded in a way that is dependent on the viewing conditions. Participants first learned dynamic novel objects, presented as animation sequences. Following learning, they were then tested on their ability to recognize these learned objects when their animation sequence was shown in the same sequence order as during learning or in the reverse sequence order. In Experiment 1, we found that non-rigid motion contributed to recognition performance; that is, sequence-reversal decreased sensitivity across different tasks. In subsequent experiments, we tested the recognition of non-rigidly deforming (Experiment 2) and rigidly rotating (Experiment 3) objects across novel viewpoints. Recognition performance was affected by viewpoint changes for both experiments. Learned non-rigid motion continued to contribute to recognition performance and this benefit was the same across all viewpoint changes. By comparison, learned rigid motion did not contribute to recognition performance. These results suggest that non-rigid motion provides a source of information for recognizing dynamic objects, which is not affected by changes to viewpoint.}, web_url = {http://www.frontiersin.org/Journal/DownloadFile.ashx?pdf=1&FileId=%2062343&articleId=%2022441&Version=%201&ContentTypeId=21&FileName=%20fncom-06-00026.pdf}, state = {published}, DOI = {10.3389/fncom.2012.00026}, author = {Chuang LL{chuang}{Department Human Perception, Cognition and Action}, Vuong QC{qvuong}{Department Human Perception, Cognition and Action} and B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action}} } @Article{ GianiOBKPN2012, title = {Steady-state responses in MEG demonstrate information integration within but not across the auditory and visual senses}, journal = {NeuroImage}, year = {2012}, month = {4}, volume = {60}, number = {2}, pages = {1478–1489}, abstract = {To form a unified percept of our environment, the human brain integrates information within and across the senses. This MEG study investigated interactions within and between sensory modalities using a frequency analysis of steady-state responses that are elicited time-locked to periodically modulated stimuli. Critically, in the frequency domain, interactions between sensory signals are indexed by crossmodulation terms (i.e. the sums and differences of the fundamental frequencies). The 3x2 factorial design, manipulated (1) modality: auditory, visual or audiovisual (2) steady-state modulation: the auditory and visual signals were modulated only in one sensory feature (e.g. visual gratings modulated in luminance at 6 Hz) or in two features (e.g. tones modulated in frequency at 40 Hz & amplitude at 0.2 Hz). This design enabled us to investigate crossmodulation frequencies that are elicited when two stimulus features are modulated concurrently (i) in one sensory modality or (ii) in auditory and visual modalities. In support of within-modality integration, we reliably identified crossmodulation frequencies when two stimulus features in one sensory modality were modulated at different frequencies. In contrast, no crossmodulation frequencies were identified when information needed to be combined from auditory and visual modalities. The absence of audiovisual crossmodulation frequencies suggests that the previously reported audiovisual interactions in primary sensory areas may mediate low level spatiotemporal coincidence detection that is prominent for stimulus transients but less relevant for sustained SSR responses. In conclusion, our results indicate that information in SSRs is integrated over multiple time scales within but not across sensory modalities at the primary cortical level.}, web_url = {http://www.sciencedirect.com/science/article/pii/S1053811912001322}, state = {published}, DOI = {10.1016/j.neuroimage.2012.01.114}, author = {Giani AS{giani}{Department Human Perception, Cognition and Action}{Research Group Cognitive Neuroimaging}, Ortiz EB, Belardinelli P, Kleiner M{kleinerm}{Department Human Perception, Cognition and Action}, Preissl H and Noppeney U{unoppe}{Research Group Cognitive Neuroimaging}} } @Inproceedings{ AlexandrovaRBTKBM2012, title = {Enhancing Medical Communication Training Using Motion Capture, Perspective Taking and Virtual Reality}, year = {2012}, month = {2}, pages = {16-22}, abstract = {The aim of this work is to increase the effectiveness of real world medical training simulations by helping trainees gain a better understanding of the importance of communication and teamwork. Therefore we develop an online application which can be used together with real world simulations to improve training. To produce the online application we reconstructed two real world scenarios (one with students and one with practitioners) in an immersive virtual environment. Our application enables the trainees to view the scenario from different perspectives or to freely explore the environment. We aim to integrate it into the medical student curriculum at the University of Tübingen.}, web_url = {http://www.nextmed.com/index.html}, editor = {Westwood, J.D. , S.W. Westwood, L. Felländer-Tsai, R.S. Haluck, R.A. Robb, S. Senger, K.G. Vosburgh}, publisher = {IOS Press}, address = {Amsterdam, Netherlands}, booktitle = {Medicine Meets Virtual Reality 19: NextMed}, event_name = {19th Medicine Meets Virtual Reality Conference (MMVR 2012)}, event_place = {Newport Beach, CA, USA}, state = {published}, ISBN = {978-1-61499-021-5}, DOI = {10.3233/978-1-61499-022-2-16}, author = {Alexandrova IV{ivelina}{Department Human Perception, Cognition and Action}, Rall M, Breidt M{mbreidt}{Department Human Perception, Cognition and Action}, Tullius G, Kloos C, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Mohler BJ{mohler}{Department Human Perception, Cognition and Action}} } @Article{ ChillerGlausSHKK2011, title = {Recognition of emotion in moving and static composite faces}, journal = {Swiss Journal of Psychology}, year = {2011}, month = {12}, volume = {70}, number = {4}, pages = {233-240}, abstract = {This paper investigates whether the greater accuracy of emotion identification for dynamic versus static expressions, as noted in previous research, can be explained through heightened levels of either component or configural processing. Using a paradigm by Young, Hellawell, and Hay (1987), we tested recognition performance of aligned and misaligned composite faces with six basic emotions (happiness, fear, disgust, surprise, anger, sadness). Stimuli were created using 3D computer graphics and were shown as static peak expressions (static condition) and 7 s video sequences (dynamic condition). The results revealed that, overall, moving stimuli were better recognized than static faces, although no interaction between motion and other factors was found. For happiness, sadness, and surprise, misaligned composites were better recognized than aligned composites, suggesting that aligned composites fuse to form a single expression, while the two halves of misaligned composites are perceived as two separate emotions. For anger, disgust, and fear, this was not the case. These results indicate that emotions are perceived on the basis of both configural and component-based information, with specific activation patterns for separate emotions, and that motion has a quality of its own and does not increase configural or component-based recognition separately.}, web_url = {http://psycnet.apa.org/journals/sjp/70/4/233.pdf}, state = {published}, DOI = {10.1024/1421-0185/a000061}, author = {Chiller-Glaus SD, Schwaninger A{aschwan}{Department Human Perception, Cognition and Action}, Hofer F, Kleiner M{kleinerm}{Department Human Perception, Cognition and Action} and Knappmeyer B{babsy}{Department Human Perception, Cognition and Action}} } @Conference{ Chuang2011_4, title = {Perception of the active observer}, year = {2011}, month = {11}, day = {2}, abstract = {As active observers, we move our eyes, re-orient our bodies and even manipulate our environment to access task-relevant information. The purpose of this talk is demonstrate that our understanding of human behavior can be enriched by considering that the observer is often-times responsible for his own perceptual input. I will do so by first presenting research that: a) addressed how object speeds are estimated during locomotion, b) investigated how we explore objects during learning for subsequent recognition. Following this, I will present research in two application scenarios that exemplifies the role of the active observer — namely, teleoperation of swarm-UAVs and gazetracking on wall-sized displays.}, web_url = {http://ikw.uni-osnabrueck.de/en/node/680}, event_name = {Institute of Cognitive Science, Universität Osnabrück}, event_place = {Osnabrück, Germany}, state = {published}, author = {Chuang L{chuang}{Department Human Perception, Cognition and Action}} } @Poster{ SchindlerKB2011, title = {Decoding egocentric space in human posterior parietal cortex using fMRI}, year = {2011}, month = {11}, volume = {41}, number = {800.21}, abstract = {In our subjective experience, there is a tight link between covert visual attention and ego-centric spatial attention. One key difference is that the latter can extend beyond the visual field, providing us with an accurate mental representation of an object’s location relative to our body position. A neural link between visual and ego-centric spatial attention is suggested by lesions in parietal cortex, that lead not only to deficits in covert visual attention, but frequently also to a disorder of ego-centric spatial awareness, known as hemi-spatial neglect. While parietal involvement in covert visual spatial attention has been much studied, relatively little is known about mental representations of the unseen space around us. In the present study we examined whether also unseen spatial locations beyond the visual field are represented in parietal activity, and how they are related to retinotopic representations. We employed a novel virtual reality (VR) paradigm during functional magnetic resonance imaging (fMRI), whereby observers were prompted to draw their spatial attention to the position of one of eight possible objects located around them in an octagonal room. By changing the observers’ facing direction every few trials, the egocentric location of objects was disentangled from their absolute position and from the objects’ identity. Thus, mental representations of egocentric space surrounding the observer were sampled eight-fold. De-coding results of a multivariate pattern analysis classifier (MVPA), but not univariate results, showed that egocentric spatial directions were specifically represented in parietal cortex. These representations overlapped only partly with visually driven retinotopic activity. Our results thus show that parietal cortex codes not only for retinotopic and visually accessible space, but also for egocentric locations of the three-dimensional space surrounding us, including unseen space.}, web_url = {http://www.sfn.org/AM2011/}, event_name = {41st Annual Meeting of the Society for Neuroscience (Neuroscience 2011)}, event_place = {Washington, DC, USA}, state = {published}, author = {Schindler A{aschindler}{Department Physiology of Cognitive Processes}, Kleiner M{kleinerm}{Department Human Perception, Cognition and Action} and Bartels A{abartels}{Department Physiology of Cognitive Processes}} } @Article{ StreuberKSBd2011, title = {The effect of social context on the use of visual information}, journal = {Experimental Brain Research}, year = {2011}, month = {10}, volume = {214}, number = {2}, pages = {273-284}, abstract = {Social context modulates action kinematics. Less is known about whether social context also affects the use of task relevant visual information. We tested this hypothesis by examining whether the instruction to play table tennis competitively or cooperatively affected the kind of visual cues necessary for successful table tennis performance. In two experiments, participants played table tennis in a dark room with only the ball, net, and table visible. Visual information about both players’ actions was manipulated by means of self-glowing markers. We recorded the number of successful passes for each player individually. The results showed that participants’ performance increased when their own body was rendered visible in both the cooperative and the competitive condition. However, social context modulated the importance of different sources of visual information about the other player. In the cooperative condition, seeing the other player’s racket had the largest effects on performance increase, whereas in the competitive condition, seeing the other player’s body resulted in the largest performance increase. These results suggest that social context selectively modulates the use of visual information about others’ actions in social interactions.}, web_url = {http://www.springerlink.com/content/b014430023h47417/fulltext.pdf}, state = {published}, DOI = {10.1007/s00221-011-2830-9}, author = {Streuber S{stst}{Department Human Perception, Cognition and Action}, Knoblich G, Sebanz N, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}} } @Inproceedings{ SonCKB2011, title = {Haptic Feedback Cues Can Improve Human Perceptual Awareness in Multi-Robots Teleoperation}, year = {2011}, month = {10}, pages = {1323-1328}, abstract = {The availability of additional force cues in haptic devices are often expected to improve control performance, over conditions that only provide visual feedback. However, there is little empirical evidence to show this to be true for the teleoperation control of remote vehicles (i.e., multiple unmanned aerial vehicles (UAVs)). In this paper, we show that force cues can increase one's sensitivity in discerning the presence of obstacles in the remote multi-UAVs' environment. Significant benefits, relative to a purely visual scenario, were achieved only when force cues were sufficiently amplified by large gains. In addition, force cues tended to provide stronger benefits when they were based on the UAVs' velocity information.}, web_url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6106130}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_name = {11th International Conference on Control, Automations and Systems (ICCAS 2011)}, event_place = {Gyeonggi-do, Korea}, state = {published}, ISBN = {978-1-4577-0835-0}, author = {Son HI{chakurt}{Department Human Perception, Cognition and Action}, Chuang L{chuang}{Department Human Perception, Cognition and Action}, Kim J{junsukkim}{Department Human Perception, Cognition and Action} and B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action}} } @Inproceedings{ LayherTSBCN2011, title = {Social Signal Processing in Companion Systems: Challenges Ahead}, year = {2011}, month = {10}, pages = {239}, abstract = {Companion technologies aim at developing sustained long-term relationships by employing emotional, nonverbal communication skills and empathy. One of the main challenges is to equip such companions with human-like abilities to reliably detect and analyze social signals. In this proposal, we focus our investigation on the modeling of visual processing mechanisms, since evidence in literature suggests that nonverbal interaction plays a key role in steering, controlling and maintaining social interaction between humans. We seek to transfer fragments of this competence to the domain of human computer interaction. Some core computational mechanisms of extracting and analyzing nonverbal signals are presented, enabling virtual agents to create socially competent response behaviors.}, file_url = {fileadmin/user_upload/files/publications/2011/Informatik-2011-Layher.pdf}, web_url = {http://www.user.tu-berlin.de/komm/CD/html/ws603.html}, editor = {Heiss , H.-U. , P. Pepper, H. Schlingloff, J. Schneider}, publisher = {Gesellschaft für Informatik}, address = {Bonn, Germany}, booktitle = {Informatik 2011: Informatik schafft Communities}, event_name = {Workshop on "Companion-Systeme und Mensch-Companion-Interaktion"}, event_place = {Berlin, Germany}, state = {published}, ISBN = {978-3-88579-286-4}, author = {Layher G, Neumann H, Scherer S, Tschechne S, Brosch T and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Poster{ SchindlerKB2011_2, title = {Decoding Egocentric Space in human Posterior Parietal Cortex using fMRI}, year = {2011}, month = {10}, volume = {12}, pages = {40}, abstract = {In our subjective experience, there is a tight link between covert visual attention and egocentric spatial attention. One key difference is that the latter can extend beyond the visual field, providing us with an acurate mental representation of an object’s location relative to our body position. A neural link between visual and ego-centric spatial attention is suggested by lesions in parietal cortex, that lead not only to deficits in covert visual attention, but frequently also to a disorder of ego-centric spatial awareness, known as hemi-spatial neglect. While parietal involvement in covert visual spatial attention has been much studied, relatively little is known about mental representations of the unseen space around. In the present study we examined whether also unseen spatial locations beyond the visual field are represented in parietal activity, and how they are related to retinotopic representations. We employed a novel virtual reality (VR) paradigm during functional magnetic resonance imaging (fMRI), whereby observers were prompted to draw their spatial attention to the position of one of eight possible objects located around them in an octagonal room. By changing the observers’ facing direction every few trials, the ego-centric location of objects was disentangled from their absolute position and from the objectsâ identity. Thus, mental representations of egocentric space surrounding the observer were sampled eight-fold. Decoding results of a multivariate pattern analysis classifier (MVPA), but not univariate results, showed that egocentric spatial directions were specifically represented in parietal cortex. These representations overlapped only partly with visually driven retinotopic activity. Our results thus show that parietal cortex codes not only for retinotopic and visually accessible space, but also for ego-centric locations of the three-dimensional space surrounding us, including unseen space.}, web_url = {http://www.neuroschool-tuebingen-nena.de/index.php?id=284}, event_name = {12th Conference of Junior Neuroscientists of Tübingen (NeNA 2011)}, event_place = {Heiligkreuztal, Germany}, state = {published}, author = {Schindler A{aschindler}{Department Physiology of Cognitive Processes}, Kleiner M{kleinerm}{Department Human Perception, Cognition and Action} and Bartels A{abartels}{Department Physiology of Cognitive Processes}} } @Poster{ LeeBBC2011, title = {Fast Fitting on a Saccadic Eye Movement Model for Decision Making}, year = {2011}, month = {10}, volume = {12}, pages = {33}, abstract = {How does our visual system decide where to look? The Linear Approach to Threshold with Ergodic Rate (LATER: Carpenter, 1995) is a simple decision-making model for saccadic eye movements. Currently, experimental data suggest that saccadic eye-movements can be discriminated according to whether they are performed for directed fixations or for item recognition (Montagnini & Chelazzi, 2005; Bieg et al., submitted). Unfortunately, sufficient goodness-of-fit can only be acquired with large datasets, for each individual participant. Here, we investigate whether adapting LATER with modern computational methods can allow for saccades to be classified for their functionality, with minimal data and in real-time. In doing so, we strive towards the eventual goal of using the LATER model for predicting observer intentions in real-world applications.}, web_url = {http://www.neuroschool-tuebingen-nena.de/index.php?id=360}, event_name = {12th Conference of Junior Neuroscientists of Tübingen (NeNA 2011)}, event_place = {Heiligkreuztal, Germany}, state = {published}, author = {Lee JJ{jlee}{Department Human Perception, Cognition and Action}, Bieg H-J{bieg}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Chuang LL{chuang}{Department Human Perception, Cognition and Action}} } @Poster{ GianiEBKPN2011, title = {Steady-state responses in MEG demonstrate information integration within but not across the auditory and visual senses}, year = {2011}, month = {10}, volume = {12}, pages = {27}, abstract = {To form a unified percept of our environment, the human brain integrates information within and across the senses. This MEG study investigated interactions within and between sensory modalities using a frequency analysis of steady-Ââstate responses (SSR) to periodic auditory and/or visual inputs. The 3x3 factorial design, manipulated (1) modality (auditory only, visual only and audiovisual) and (2) temporal dynamics (static, dynamic1 and dynamic2). In the static conditions, subjects were presented with (1) visual gratings, luminance modulated at 6Hz and/or (2) pure tones, frequency modulated at 40 Hz. To manipulate perceptual synchrony, we imposed additional slow modulations on the auditory and visual stimuli either at same (0.2 Hz = synchronous) or different frequencies (0.2 Hz vs. 0.7 Hz = asynchronous). This also enabled us to investigate the integration of two dynamic features within one sensory modality (e.g. a pure tone frequency modulated at 40Hz & amplitude modulated at 0.2Hz) in the dynamic conditions. We reliably identified crossmodulation frequencies when these two stimulus features were modulated at different frequencies. In contrast, no crossmodulation frequencies were identified when information needed to be combined from auditory and visual modalities. The absence of audiovisual crossmodulation frequencies suggests that the previously reported audiovisual interactions in primary sensory areas may mediate low level spatiotemporal coincidence detection that is prominent for stimulus transients but less relevant for sustained SSR responses. In conclusion, our results indicate that information in SSRs is integrated over multiple time scales within but not across sensory modalities at the primary cortical level.}, web_url = {http://www.neuroschool-tuebingen-nena.de/index.php?id=284}, event_name = {12th Conference of Junior Neuroscientists of Tübingen (NeNA 2011)}, event_place = {Heiligkreuztal, Germany}, state = {published}, author = {Giani A{giani}{Department Human Perception, Cognition and Action}{Research Group Cognitive Neuroimaging}, Erick O, Belardinelli P, Kleiner M{kleinerm}{Department Human Perception, Cognition and Action}, Preissl H and Noppeney U{unoppe}{Research Group Cognitive Neuroimaging}} } @Conference{ Kleiner2011, title = {Fairy tales & horror stories: Common misconceptions and traps about use of computers for psychophysical testing}, year = {2011}, month = {10}, volume = {12}, pages = {10}, abstract = {This talk will describe some very common misconceptions that cognitive neuroscientists frequently express about the use of computers and related equipment for visual or auditory stimulus presentation, response collection and the timing precision and behaviour of computers and common operating systems in general. Some typical examples are assumptions about the suitability of LCD flat panels for timed and controlled visual stimulation, naive use of standard sound cards for timed auditory stimulation, and the use of keyboards and mice for reaction time measurements. The talk will try to point out solutions or remedies for some problems where available. The examples are based on an informal sampling of questions asked and misconceptions often encountered on the Psychtoolbox user forum.}, web_url = {http://www.neuroschool-tuebingen-nena.de/index.php?id=284}, event_name = {12th Conference of Junior Neuroscientists of Tübingen (NeNA 2011)}, event_place = {Heiligkreuztal, Germany}, state = {published}, author = {Kleiner M{kleinerm}{Department Human Perception, Cognition and Action}} } @Conference{ Chuang2011_3, title = {Moving objects: From object speed estimation to object exploration}, year = {2011}, month = {10}, web_url = {http://www.liv.ac.uk/psychology/}, event_name = {Department of Psychology, University of Liverpool}, event_place = {Liverpool, UK}, state = {published}, author = {Chuang L{chuang}{Department Human Perception, Cognition and Action}} } @Conference{ Chuang2011_2, title = {The active observer: Implications for science and engineering}, year = {2011}, month = {10}, web_url = {http://www.tno.nl/content.cfm?context=thema&content=markt_product&laag1=892&laag2=184&laag3=401&item_id=1581&Taal=1}, event_name = {TNO Human Factors}, event_place = {Soesterberg, Netherlands}, state = {published}, author = {Chuang L{chuang}{Department Human Perception, Cognition and Action}} } @Inproceedings{ EngelBHC2011, title = {Image Retrieval with Semantic Sketches}, year = {2011}, month = {9}, pages = {412-425}, abstract = {With increasingly large image databases, searching in them becomes an ever more difficult endeavor. Consequently, there is a need for advanced tools for image retrieval in a webscale context. Searching by tags becomes intractable in such scenarios as large numbers of images will correspond to queries such as “car and house and street”. We present a novel approach that allows a user to search for images based on semantic sketches that describe the desired composition of the image. Our system operates on images with labels for a few high-level object categories, allowing us to search very fast with a minimal memory footprint. We employ a structure similar to random decision forests which avails a data-driven partitioning of the image space providing a search in logarithmic time with respect to the number of images. This makes our system applicable for large scale image search problems. We performed a user study that demonstrates the validity and usability of our approach.}, web_url = {http://interact2011.org/}, editor = {Campos, P. , N. Graham, J. Jorge, N. Nunes, P. Palanque, M. Winckler}, publisher = {Springer}, address = {Berlin, Germany}, booktitle = {Human-Computer Interaction: INTERACT 2011}, event_name = {13th IFIP TC13 Conference on Human-Computer Interaction}, event_place = {Lisboa, Portugal}, state = {published}, ISBN = {978-3-642-23774-4}, DOI = {10.1007/978-3-642-23774-4_35}, author = {Engel D{engel}{Department Human Perception, Cognition and Action}, Herdtweck C{grueschaan}{Department Human Perception, Cognition and Action}, Browatzki B{browatbn}{Department Human Perception, Cognition and Action} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Inproceedings{ SonCFKLLBR2011, title = {Measuring an Operator's Maneuverability Performance in the Haptic Teleoperation of Multiple Robots}, year = {2011}, month = {9}, pages = {3039-3046}, abstract = {In this paper, we investigate the maneuverability performance of human teleoperators on multi-robots. First, we propose that maneuverability performance can be assessed by a frequency response function that jointly considers the input force of the operator and the position errors of the multi-robot system that is being maneuvered. Doing so allows us to evaluate maneuverability performance in terms of the human teleoperator's interaction with the controlled system. This allowed us to effectively determine the suitability of different haptic cue algorithms in improving teleoperation maneuverability. Performance metrics based on the human teleoperator's frequency response function indicate that maneuverability performance is best supported by a haptic feedback algorithm which is based on an obstacle avoidance force.}, file_url = {fileadmin/user_upload/files/publications/2011/IROS-2011-Son.pdf}, web_url = {http://www.iros2011.org/}, editor = {Amato, N.M.}, publisher = {IEEE}, address = {Piscatawy, NJ, USA}, event_name = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011)}, event_place = {San Francisco, CA, USA}, state = {published}, ISBN = {978-1-61284-454-1}, DOI = {10.1109/IROS.2011.6048185}, author = {Son HI{chakurt}{Department Human Perception, Cognition and Action}, Chuang LL{chuang}{Department Human Perception, Cognition and Action}, Franchi A{antonio}{Department Human Perception, Cognition and Action}, Kim J{junsukkim}{Department Human Perception, Cognition and Action}, Lee D, Lee S-W, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Robuffo Giordano P{robu_pa}{Department Human Perception, Cognition and Action}} } @Poster{ DobsKBSC2011, title = {Investigating idiosyncratic facial dynamics with motion retargeting}, journal = {Perception}, year = {2011}, month = {9}, volume = {40}, number = {ECVP Abstract Supplement}, pages = {115}, abstract = {3D facial animation systems allow the creation of well-controlled stimuli to study face processing. Despite this high level of control, such stimuli often lack naturalness due to artificial facial dynamics (eg linear morphing). The present study investigates the extent to which human visual perception can be fooled by artificial facial motion. We used a system that decomposes facial motion capture data into time courses of basic action shapes (Curio et al, 2006 APGV 1 77–84). Motion capture data from four short facial expressions were input to the system. The resulting time courses and five approximations were retargeted onto a 3D avatar head using basic action shapes created manually in Poser. Sensitivity to the subtle modifications was measured in a matching task using video sequences of the actor performing the corresponding expressions as target. Participants were able to identify the unmodified retargeted facial motion above chance level under all conditions. Furthermore, matching performance for the different approximations varied with expression. Our findings highlight the sensitivity of human perception for subtle facial dynamics. Moreover, the action shape-based system will allow us to further investigate the perception of idiosyncratic facial motion using well-controlled facial animation stimuli.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v110293}, event_name = {34th European Conference on Visual Perception}, event_place = {Toulouse, France}, state = {published}, author = {Dobs K{kdobs}{Department Human Perception, Cognition and Action}, Kleiner M{kleinerm}{Department Human Perception, Cognition and Action}, B\"ulthoff I{isa}{Department Human Perception, Cognition and Action}, Schultz J{johannes}{Department Human Perception, Cognition and Action} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Poster{ ChuangS2011, title = {Object speed estimation during walking does not add up}, year = {2011}, month = {9}, web_url = {http://www.bccn-tuebingen.de/news/article/symposium-imultisensory-perception-and-actioni-96.html}, event_name = {Bernstein Cluster D Symposium: Multisensory Perception and Action}, event_place = {Tübingen, Germany}, state = {published}, author = {Chuang LL{chuang}{Department Human Perception, Cognition and Action} and Souman JL{souman}{Department Human Perception, Cognition and Action}} } @Poster{ ChuangBS2011, title = {The center-surround effect in visual speed estimation during walking}, journal = {Perception}, year = {2011}, month = {9}, volume = {40}, number = {ECVP Abstract Supplement}, pages = {129}, abstract = {Walking reduces visual speed estimates of optic flow (Souman et al, 2010 Journal of Vision 10(11):14]. Simultaneously, visual background motion can influence the perceived speed of moving objects (Tynan and Sekular, 1975 Vision Research 25 1231–1238; Baker and Graf, 2010 Vision Research 50 193–201). These two effects have been attributed to different subtractive processes, which may help in segregating object motion from self-motion induced optic flow. Here, we investigate how both factors jointly contribute to the perceived visual speed of objects. Participants compared the speed of two central Gabor patches on a ground plane, presented in consecutive intervals, either while standing still or while walking on a treadmill. In half the trials, one of the Gabors was surrounded by a moving random dot pattern, the speed of which matched walking speed. Our results replicated previous findings. A moving surround as well as walking can independently induce a subtractive effect on the perceived speed of the moving center, with the effect size increasing with center speed. However, walking does not affect visual speed estimates of the center when a visual surround is present. These results suggest that the visual input dominates the segregation of object motion from background optic flow.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v110345}, event_name = {34th European Conference on Visual Perception}, event_place = {Toulouse, France}, state = {published}, author = {Chuang L{chuang}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Souman J{souman}{Department Human Perception, Cognition and Action}} } @Poster{ Streuberd2011, title = {The effect of visual information on motor control in social interaction tasks}, journal = {Perception}, year = {2011}, month = {9}, volume = {40}, number = {ECVP Abstract Supplement}, pages = {226}, abstract = {Seeing an object is important for motor control during object interaction. Which sources of visual information are important for motor control in social interaction? In a virtual environment participants hit table tennis balls served by a virtual player. We manipulated the visibility of visual information (ball, racket, body) about the virtual player and the presentation time of the animation (before, during, and after the virtual player’s stroke). We measured the shortest distance between the ball and the participants’ racket. Results: (1) The visibility of each source of information was associated with performance increases; (2) performance did not change when visual information was presented after the virtual player hit the ball; (3) the presentation of the virtual player's racket induced the largest performance improvement shortly before the virtual player hit the ball; (4) performance changes associated with seeing the virtual player’s body were independent of presentation time. In sum participants seem to use multiple sources of visual information about the interaction partner. Moreover visual information about the interaction partner is most useful when seen before the interaction partner's stroke. These results support the hypothesis that the perception of the virtual player affects the online control of own actions.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v110430}, event_name = {34th European Conference on Visual Perception}, event_place = {Toulouse, France}, state = {published}, author = {Streuber S{stst}{Department Human Perception, Cognition and Action} and de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}} } @Poster{ delaRosaGC2011, title = {The influence of dynamic and static adaptors on the magnitude of high-level aftereffects for dynamic facial expression}, journal = {Perception}, year = {2011}, month = {9}, volume = {40}, number = {ECVP Abstract Supplement}, pages = {154}, abstract = {Adapting to an emotional facial expression biases emotional judgments of an ambiguous facial expression away from the adapted facial expression. Previous studies examining emotional facial adaptation effects used static emotional facial expressions as adaptors. Since natural facial expressions are inherently dynamic, dynamic information might enhance the magnitude of the emotional facial expression adaptation effect. We tested this hypothesis by comparing emotional facial expression adaptation effects for static and dynamic facial expression adaptors. Stimuli were generated using a dynamic 3D morphable face model. We found adaptation effects of similar magnitude for dynamic and static adaptors. When rigid head motion was removed (leaving only non-rigid intrinsic facial motion cues), the adaptation effects with dynamic adaptors disappeared. These results obtained with a novel method for the synthesis of facial expression stimuli suggest that at least part of the cognitive representation of facial expressions is dynamic and depends on head motion.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v110545}, event_name = {34th European Conference on Visual Perception}, event_place = {Toulouse, France}, state = {published}, author = {de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}, Giese MA{giese} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Poster{ KaularddSFBW2011, title = {What are the properties underlying similarity judgments of facial expressions?}, journal = {Perception}, year = {2011}, month = {9}, volume = {40}, number = {ECVP Abstract Supplement}, pages = {115}, abstract = {Similarity ratings are used to investigate the cognitive representation of facial expressions. The perceptual and cognitive properties (eg physical aspects, motor expressions, action tendencies) driving the similarity judgments of facial expressions are largely unknown. We examined potentially important properties with 27 questions addressing the emotional and conversational content of expressions (semantic differential). The ratings of these semantic differentials were used as predictors for facial expression similarity ratings. The semantic differential and similarity-rating task were performed on the same set of facial expression videos: 6 types of emotional (eg happy) and 6 types of conversational (eg don’t understand) expressions. Different sets of participants performed the two tasks. Multiple regression was used to predict the similarity data from the semantic differential questions. The best model for emotional expressions consisted of two emotional questions explaining 75% of the variation in similarity ratings. The same model explained significantly less variation for conversational expressions (38%). The best model for those expressions consisted of a single conversational question explaining 44% of the variation. This study shows which properties of facial expressions might affect their perceived similarity. Moreover, our results suggest that different perceptual and cognitive properties might underlie similarity judgments about emotional and conversational expressions.}, web_url = {http://www.perceptionweb.com/abstract.cgi?id=v110290}, event_name = {34th European Conference on Visual Perception}, event_place = {Toulouse, France}, state = {published}, author = {Kaulard K{kascot}{Department Human Perception, Cognition and Action}, de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}, Schultz J{johannes}{Department Human Perception, Cognition and Action}, Fernandez Cruz AL{anafer}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Wallraven C{walli}{Department Human Perception, Cognition and Action}} } @Conference{ Chuang2011, title = {How do we seek out information?}, year = {2011}, month = {8}, day = {29}, abstract = {Many tasks require us to access relevant information from a dynamic visual input. To do so, we move our eyes and bodies as well as manipulate our environments. Unfortunately, experiments on human behavior tend to ignore this fact, often to the detriment of their ecological validity. Our understanding can be better informed by studying how humans actively seek out relevant information in their unrestrained and task-relevant workspaces. I will present several research studies from our lab to demonstrate this point. These studies relate to how humans explore novel objects, unrestrained gaze measurements on wall-sized displays, and the influence of haptic force feedback on the teleoperation of micro unmanned aerial vehicles. Finally, I will introduce our latest research project that targets the implications of a personal air transport system (www.mycopter.eu).}, file_url = {fileadmin/user_upload/files/publications/2011/D-CIS-Lab-2011-Chuang.pdf}, web_url = {http://www.d-cis.nl/news/210-colloquium-how-do-we-seek-out-information-}, event_name = {D-CIS Lab Colloquium}, event_place = {Delft, Netherlands}, state = {published}, author = {Chuang L{chuang}{Department Human Perception, Cognition and Action}} } @Inproceedings{ McManusBSdBM2011, title = {The influence of avatar (self and character) animations on distance estimation, object interaction and locomotion in immersive virtual environments}, year = {2011}, month = {8}, pages = {37-44}, abstract = {Humans have been shown to perceive and perform actions differently in immersive virtual environments (VEs) as compared to the real world. Immersive VEs often lack the presence of virtual characters; users are rarely presented with a representation of their own body and have little to no experience with other human avatars/characters. However, virtual characters and avatars are more often being used in immersive VEs. In a two-phase experiment, we investigated the impact of seeing an animated character or a self-avatar in a head-mounted display VE on task performance. In particular, we examined performance on three different behavioral tasks in the VE. In a learning phase, participants either saw a character animation or an animation of a cone. In the task performance phase, we varied whether participants saw a co-located animated self-avatar. Participants performed a distance estimation, an object interaction and a stepping stone locomotion task within the VE. We find no impact of a character animation or a self-avatar on distance estimates. We find that both the animation and the self-avatar influenced task performance which involved interaction with elements in the environment; the object interaction and the stepping stone tasks. Overall the participants performed the tasks faster and more accurately when they either had a self-avatar or saw a character animation. The results suggest that including character animations or self-avatars before or during task execution is beneficial to performance on some common interaction tasks within the VE. Finally, we see that in all cases (even without seeing a character or self-avatar animation) participants learned to perform the tasks more quickly and/or more accurately over time.}, web_url = {http://www.apgv.org/archive/apgv11/}, publisher = {ACM Press}, address = {New York, NY, USA}, event_name = {8th Symposium on Applied Perception in Graphics and Visualization (APGV 2011)}, event_place = {Toulouse, France}, state = {published}, ISBN = {978-1-4503-0889-2}, DOI = {10.1145/2077451.2077458}, author = {McManus EA, Bodenheimer B, Streuber S{stst}{Department Human Perception, Cognition and Action}, de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Mohler BJ{mohler}{Department Human Perception, Cognition and Action}} } @Conference{ Breidt2011_2, title = {3D-Mimikanalyse}, year = {2011}, month = {7}, event_name = {Tübinger Innovationstage 2011 der Industrie- und Handelskammer Reutlingen}, event_place = {Tübingen, Germany}, state = {published}, author = {Breidt M{mbreidt}{Department Human Perception, Cognition and Action}} } @Inproceedings{ SonKCFRLB2011, title = {An Evaluation of Haptic Cues on the Tele-Operator's Perceptual Awareness of Multiple UAVs' Environments}, year = {2011}, month = {6}, pages = {149-154}, abstract = {The use of multiple unmanned aerial vehicles (UAVs) is increasingly being incorporated into a wide range of teleoperation applications. To date, relevant research has largely been focused on the development of appropriate control schemes. In this paper, we extend previous research by investigating how control performance could be improved by providing the teleoperator with haptic feedback cues. First, we describe a control scheme that allows a teleoperator to manipulate the flight of multiple UAVs in a remote environment. Next, we present three designs of haptic cue feedback that could increase the teleoperator's environmental awareness of such a remote environment. These cues are based on the UAVs' i) velocity information, ii) proximity to obstacles, and iii) a combination of these two sources of information. Finally, we present an experimental evaluation of these haptic cue designs. Our evaluation is based on the teleoperator's perceptual sensitivity to the physical environment inhabited by the multiple UAVs. We conclude that a teleoperator's perceptual sensitivity is best served by haptic feedback cues that are based on the velocity information of multiple UAVs.}, file_url = {fileadmin/user_upload/files/publications/2011/WHC-2011-Son.pdf}, web_url = {http://www.haptics2011.org/en/}, editor = {Jones, L. , M. Harders, Y. Yokokohji}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_name = {IEEE 2011 World Haptics Conference (WHC 2011)}, event_place = {Istanbul, Turkey}, state = {published}, ISBN = {978-1-4577-0299-0}, DOI = {10.1109/WHC.2011.5945477}, author = {Son HI{chakurt}{Department Human Perception, Cognition and Action}, Kim J{junsukkim}{Department Human Perception, Cognition and Action}, Chuang LL{chuang}{Department Human Perception, Cognition and Action}, Franchi A{antonio}{Department Human Perception, Cognition and Action}, Robuffo Giordano P{robu_pa}{Department Human Perception, Cognition and Action}, Lee D and B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action}} } @Inproceedings{ EngelC2011_2, title = {Pedestrian Detectability: Predicting Human Perception Performance with Machine Vision}, year = {2011}, month = {6}, pages = {429-435}, abstract = {How likely is it that a driver notices a person standing on the side of the road? In this paper we introduce the concept of pedestrian detectability. It is a measure of how probable it is that a human observer perceives pedestrians in an image. We acquire a dataset of pedestrians with their associated detectabilities in a rapid detection experiment using images of street scenes. On this dataset we learn a regression function that allows us to predict human detectabilities from an optimized set of image and contextual features. We exploit this function to infer the optimal focus of attention for pedestrian detection. With this combination of human perception and machine vision we propose a method we deem useful for the optimization of Human-Machine-Interfaces in driver assistance systems.}, file_url = {fileadmin/user_upload/files/publications/2011/IV-2011-Engel.pdf}, web_url = {http://www.mrt.uni-karlsruhe.de/iv2011/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_name = {IEEE Intelligent Vehicles Symposium (IV 2011)}, event_place = {Baden-Baden, Germany}, state = {published}, ISBN = {978-1-4577-0890-9}, DOI = {10.1109/IVS.2011.5940445}, author = {Engel D{engel}{Department Human Perception, Cognition and Action} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Poster{ GianiOBKPN2011, title = {Using steady state responses in MEG to study information integration within and across the senses}, year = {2011}, month = {6}, number = {1028}, abstract = {How does the brain integrate information within and across sensory modalities to form a unified percept? This question has previously been addressed using transient stimuli, analyzed in the time domain. Alternatively, sensory interactions can be investigated using frequency analyses of steady state responses (SSRs). SSRs are elicited by periodic sensory stimulation (such as frequency modulated tones). In the frequency domain, 'true' signal integration is reflected by non-linear crossmodulation terms (i.e. the sums and differences of the individual SSR frequencies). In addition, two signals may modulate the amplitude of the fundamental and harmonic frequencies of one another. Using visual (V) and auditory (A) SSRs, we investigated whether A and V signals are truly integrated as indexed by crossmodulation terms or simply modulate the expression of each other's dominant frequencies. To manipulate perceptual synchrony, we imposed additional slow modulations on the auditory and visual SSRs either at same or different frequencies. This also enabled us to investigate the integration of two dynamic features within one sensory modality.}, file_url = {fileadmin/user_upload/files/publications/2011/HBM-2011-Giani.pdf}, web_url = {http://www.humanbrainmapping.org/i4a/pages/index.cfm?pageID=3419}, event_name = {17th Annual Meeting of the Organization for Human Brain Mapping (HBM 2011)}, event_place = {Québec City, Canada}, state = {published}, author = {Giani AS{giani}{Department Human Perception, Cognition and Action}{Research Group Cognitive Neuroimaging}, Ortiz EB, Belardinelli P, Kleiner M{kleinerm}{Department Human Perception, Cognition and Action}, Preissl H and Noppeney U{unoppe}{Research Group Cognitive Neuroimaging}} } @Inproceedings{ AlexandrovaRBKTBM2011, title = {Animations of Medical Training Scenarios in Immersive Virtual Environments}, year = {2011}, month = {5}, pages = {9-12}, abstract = {Medical training centers often provide various simulations for students and professionals. Their goal is not only to make trainees practice specific scenarios but also to help them effectively transfer the acquired skills to the real world. Having in mind that virtual environments have already been acknowledged for their potential to improve the medical training process, we propose an approach for rapid generation of animated medical scenarios, which can be used as an additional training tool that fits into the time frame of a semester training program.}, file_url = {fileadmin/user_upload/files/publications/2011/CASA-2011-Alexandrova.pdf}, web_url = {http://www.cad.zju.edu.cn/casa2011/program.html}, editor = {Liu, Y. , A. El Rhalibi, L. Li, M. Zhang, Z. Pan}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_name = {2011 Workshop on Digital Media and Digital Content Management (DMDCM)}, event_place = {Hangzhou, Zhejiang, China}, state = {published}, ISBN = {978-1-4577-0271-6}, DOI = {10.1109/DMDCM.2011.64}, author = {Alexandrova IV{ivelina}{Department Human Perception, Cognition and Action}, Rall M, Breidt M{mbreidt}{Department Human Perception, Cognition and Action}, Kloos U, Tullius G, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Mohler BJ{mohler}{Department Human Perception, Cognition and Action}} } @Inproceedings{ DoddsMdSB2011, title = {Embodied Interaction in Immersive Virtual Environments with Real Time Self-animated Avatars}, year = {2011}, month = {5}, pages = {132-135}, abstract = {This paper outlines our recent research that is providing users with a 3D avatar representation, and in particular focuses on studies in which the avatar is self-animated in real time. We use full body motion tracking, so when participants move their hands and feet, these movements are mapped onto the avatar. In a recent study (Dodds et al., CASA 2010), we found that a self-animated avatar aided participants in a communication task in a head-mounted display immersive virtual environment (VE). From the perspective of communication, we discovered it was not only important for the person speaking to be self-animated, but also for the person listening to us. Further, we show the potential of immersive VEs for investigating embodied interaction, and highlight possibilities for future research.}, file_url = {fileadmin/user_upload/files/publications/2011/CHI-2011-Dodds.pdf}, web_url = {http://www.antle.iat.sfu.ca/chi2011_EmbodiedWorkshop/}, web_url2 = {http://www.elisevandenhoven.com/publications/antle-chi11wp.pdf}, editor = {Antle A.N. , P. Marshall P, E. Van Den Hoven}, publisher = {ACM Press}, address = {New York, NY, USA}, event_name = {Workshop Embodied Interaction: Theory and Practice in HCI (CHI 2011)}, event_place = {Vancouver, BC}, state = {published}, author = {Dodds TJ{dodds}{Department Human Perception, Cognition and Action}, Mohler BJ{mohler}{Department Human Perception, Cognition and Action}, de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}, Streuber S{stst}{Department Human Perception, Cognition and Action} and B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action}} } @Conference{ WallravenC2011, title = {Non-accidental properties determine object exploration patterns}, year = {2011}, month = {5}, pages = {1-2}, file_url = {fileadmin/user_upload/files/publications/2011/ICCNS-2011-Wallraven.pdf}, web_url = {http://cns.bu.edu/cns-meeting/2011conference.html}, event_name = {15th International Conferece on Cognitive and Neural Systems (ICCNS 2011)}, event_place = {Boston, MA, USA}, state = {published}, author = {Wallraven C{walli}{Department Human Perception, Cognition and Action} and Chuang L{chuang}{Department Human Perception, Cognition and Action}} } @Inproceedings{ 7016, title = {Robust Semantic Analysis by Synthesis of 3D Facial Motion}, journal = {Proceedings of the Ninth IEEE International Conference on Automatic Face and Gesture Recognition (FG 2011)}, year = {2011}, month = {3}, pages = {713-719}, abstract = {Rich face models already have a large impact on the fields of computer vision, perception research, as well as computer graphics and animation. Attributes such as descriptiveness, semantics, and intuitive control are desirable properties but hard to achieve. Towards the goal of building such high-quality face models, we present a 3D model-based analysis-by-synthesis approach that is able to parameterize 3D facial surfaces, and that can estimate the state of semantically meaningful components, even from noisy depth data such as that produced by Time-of-Flight (ToF) cameras or devices such as Microsoft Kinect. At the core, we present a specialized 3D morphable model (3DMM) for facial expression analysis and synthesis. In contrast to many other models, our model is derived from a large corpus of localized facial deformations that were recorded as 3D scans from multiple identities. This allows us to analyze unstructured dynamic 3D scan data using a modified Iterative Closest Point model fitting process, followed by a constrained Action Unit model regression, resulting in semantically meaningful facial deformation time courses. We demonstrate the generative capabilities of our 3DMMs for facial surface reconstruction on high and low quality surface data from a ToF camera. The analysis of simultaneous recordings of facial motion using passive stereo and noisy Time-of-Flight camera shows good agreement of the recovered facial semantics.}, web_url = {http://www.fg2011.org/}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, event_name = {Ninth IEEE International Conference on Automatic Face & Gesture Recognition and Workshops (FG 2011)}, event_place = {Santa Barbara, CA, USA}, state = {published}, ISBN = {978-1-4244-9140-7}, DOI = {10.1109/FG.2011.5771336}, author = {Breidt M{mbreidt}{Department Human Perception, Cognition and Action}, B\"ulthoff HH{hhb}{Department Human Perception, Cognition and Action} and Curio C{curio}{Department Human Perception, Cognition and Action}} } @Conference{ Curio2011, title = {Perceptual Graphics: Revealing the Algorithms of Perception}, year = {2011}, month = {3}, event_name = {University of Southern California, Institute of Creative Technologies (ICT)}, event_place = {Los Angeles, CA, USA}, state = {published}, author = {Curio C{curio}{Department Human Perception, Cognition and Action}} } @Conference{ Breidt2011, title = {Robust Semantic Analysis by Synthesis of 3D Facial Motion}, year = {2011}, month = {3}, event_name = {University of Southern California, Institute of Creative Technologies (ICT)}, event_place = {Los Angeles, CA, USA}, state = {published}, author = {Breidt M{mbreidt}{Department Human Perception, Cognition and Action}} } @Article{ delaRosaCC2011, title = {Visual object detection, categorization, and identification tasks are associated with different time courses and sensitivities}, journal = {Journal of Experimental Psychology: Human Perception and Performance}, year = {2011}, month = {2}, volume = {37}, number = {1}, pages = {38-47}, abstract = {Recent evidence suggests that the recognition of an object's presence and its explicit recognition are temporally closely related. Here we re-examined the time course (using a fine and a coarse temporal resolution) and the sensitivity of three possible component processes of visual object recognition. In particular, participants saw briefly presented (Experiment I to III) or noise masked (Experiment IV) static images of objects and non-object textures. Participants reported the presence of an object, its basic level category, and its subordinate category while we measured recognition performance by means of accuracy and reaction times. All three recognition tasks were clearly separable in terms of their time course and sensitivity. Finally, the use of a coarser temporal sampling of presentation times decreased performance differences between the detection and basic level categorization task suggesting that a fine temporal sampling for the dissociation of recognition performances is important. Overall the three probed recognition processes were associated with different time courses and sensitivities.}, web_url = {http://psycnet.apa.org/journals/xhp/37/1/38.pdf}, state = {published}, DOI = {10.1037/a0020553}, author = {de la Rosa S{delarosa}{Department Human Perception, Cognition and Action}, Choudhery RN{choudhery}{Department Human Perception, Cognition and Action} and Chatziastros A{astros}{Department Human Perception, Cognition and Action}} } @Thesis{ Chuang2011_5, title = {Recognizing Objects From Dynamic Visual Experiences}, year = {2011}, web_url = {http://www.logos-verlag.de/cgi-bin/buch/isbn/2842}, state = {published}, type = {PhD}, author = {Chuang LL{chuang}{Department Human Perception, Cognition and Action}} }