journal articles
 | Tobias Loetscher; Michael Nicholls; Nicole Thomas; Andreas Bulling; Gayle Clarke; Allison Hayes; Celia Chen Using eye-tracking glasses to evaluate the effect of visual scanning training on everyday activities Journal Article Brain Impairment, 14 (2), pp. 354-355, 2013. @article{Loetscher_BI13, title = {Using eye-tracking glasses to evaluate the effect of visual scanning training on everyday activities}, author = {Tobias Loetscher and Michael Nicholls and Nicole Thomas and Andreas Bulling and Gayle Clarke and Allison Hayes and Celia Chen}, url = {//perceptual.mpi-inf.mpg.de/files/2015/06/Loetscher-Brain-Impairment-2013.pdf}, year = {2013}, date = {2013-09-01}, journal = {Brain Impairment}, volume = {14}, number = {2}, pages = {354-355}, abstract = {Screening for cognitive impairment may help predict neurorehabilitation outcomes. We investigated (1) the use of the ACE-R in predicting functional gain during in-patient rehabilitation, and (2) whether ACE-R scores identified patients requiring additional therapy support during their admission.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Screening for cognitive impairment may help predict neurorehabilitation outcomes. We investigated (1) the use of the ACE-R in predicting functional gain during in-patient rehabilitation, and (2) whether ACE-R scores identified patients requiring additional therapy support during their admission. |
conference papers
 | Jayson Turner; Andreas Bulling; Jason Alexander; Hans Gellersen Eye Drop: An Interaction Concept for Gaze-Supported Point-to-Point Content Transfer Inproceedings Proc. of the 12th International Conference on Mobile and Ubiquitous Multimedia (MUM 2013), ACM, New York, NY, USA, 2013, ISBN: 978-1-4503-2648-3. @inproceedings{turner13_mum, title = {Eye Drop: An Interaction Concept for Gaze-Supported Point-to-Point Content Transfer}, author = { Jayson Turner and Andreas Bulling and Jason Alexander and Hans Gellersen}, url = {//dx.doi.org/10.1145/2541831.2541868 //perceptual.mpi-inf.mpg.de/files/2014/10/turner13_mum.pdf}, isbn = {978-1-4503-2648-3}, year = {2013}, date = {2013-12-02}, booktitle = {Proc. of the 12th International Conference on Mobile and Ubiquitous Multimedia (MUM 2013)}, number = {37}, publisher = {ACM}, address = {New York, NY, USA}, abstract = {The shared displays in our environment contain content that we desire. Furthermore, we often acquire content for a specific purpose, i.e., the acquisition of a phone number to place a call. We have developed a content transfer concept, Eye Drop. Eye Drop provides techniques that allow fluid content acquisition, transfer from shared displays, and local positioning on personal devices using gaze combined with manual input. The eyes naturally focus on content we desire. Our techniques use gaze to point remotely, removing the need for explicit pointing on the user\'s part. A manual trigger from a personal device confirms selection. Transfer is performed using gaze or manual input to smoothly transition content to a specific location on a personal device. This work demonstrates how techniques can be applied to acquire and apply actions to content through a natural sequence of interaction. We demonstrate a proof of concept prototype through five implemented application scenarios.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } The shared displays in our environment contain content that we desire. Furthermore, we often acquire content for a specific purpose, i.e., the acquisition of a phone number to place a call. We have developed a content transfer concept, Eye Drop. Eye Drop provides techniques that allow fluid content acquisition, transfer from shared displays, and local positioning on personal devices using gaze combined with manual input. The eyes naturally focus on content we desire. Our techniques use gaze to point remotely, removing the need for explicit pointing on the user's part. A manual trigger from a personal device confirms selection. Transfer is performed using gaze or manual input to smoothly transition content to a specific location on a personal device. This work demonstrates how techniques can be applied to acquire and apply actions to content through a natural sequence of interaction. We demonstrate a proof of concept prototype through five implemented application scenarios. |
 | Gilles Bailly; Antti Oulasvirta; Timo Kötzing; Sabrina Hoppe MenuOptimizer: interactive optimization of menu systems Inproceedings Proceedings of the 26th annual ACM symposium on User interface software and technology (UIST 2013), pp. 331-342, ACM, New York, NY, USA, 2013, ISBN: 978-1-4503-2268-3. @inproceedings{Bailly13_uist, title = {MenuOptimizer: interactive optimization of menu systems}, author = {Gilles Bailly and Antti Oulasvirta and Timo Kötzing and Sabrina Hoppe}, url = {//doi.acm.org/10.1145/2501988.2502024 //gillesbailly.fr/menuoptimizer.html //gillesbailly.fr/publis/BAILLY_MenuOptimizer.pdf}, isbn = {978-1-4503-2268-3}, year = {2013}, date = {2013-10-10}, booktitle = {Proceedings of the 26th annual ACM symposium on User interface software and technology (UIST 2013)}, pages = {331-342}, publisher = {ACM}, address = {New York, NY, USA}, abstract = {Menu systems are challenging to design because design spaces are immense, and several human factors affect user behavior. This paper contributes to the design of menus with the goal of interactively assisting designers with an optimizer in the loop. To reach this goal, 1) we extend a predictive model of user performance to account for expectations as to item groupings; 2) we adapt an ant colony optimizer that has been proven efficient for this class of problems; and 3) we present MenuOptimizer, a set of interactions integrated into a real interface design tool (QtDesigner). MenuOptimizer supports designers’ abilities to cope with uncertainty and recognize good solutions. It alows designers to delegate combinatorial problems to the optimizer, which should solve them quickly enough without disrupting the design process. We show evidence that satisfactory menu designs can be produced for complex problems in minutes.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Menu systems are challenging to design because design spaces are immense, and several human factors affect user behavior. This paper contributes to the design of menus with the goal of interactively assisting designers with an optimizer in the loop. To reach this goal, 1) we extend a predictive model of user performance to account for expectations as to item groupings; 2) we adapt an ant colony optimizer that has been proven efficient for this class of problems; and 3) we present MenuOptimizer, a set of interactions integrated into a real interface design tool (QtDesigner). MenuOptimizer supports designers’ abilities to cope with uncertainty and recognize good solutions. It alows designers to delegate combinatorial problems to the optimizer, which should solve them quickly enough without disrupting the design process. We show evidence that satisfactory menu designs can be produced for complex problems in minutes. |
 | Ken Pfeuffer; Mélodie Vidal; Jayson Turner; Andreas Bulling; Hans Gellersen Pursuit Calibration: Making Gaze Calibration Less Tedious and More Flexible Inproceedings Proc. of the 26th ACM Symposium on User Interface Software and Technology (UIST 2013), pp. 261-270 , 2013. @inproceedings{pfeuffer13_uist, title = {Pursuit Calibration: Making Gaze Calibration Less Tedious and More Flexible}, author = {Ken Pfeuffer and Mélodie Vidal and Jayson Turner and Andreas Bulling and Hans Gellersen}, url = {//dx.doi.org/10.1145/2501988.2501998 //perceptual.mpi-inf.mpg.de/files/2013/10/pfeuffer13_uist.pdf //www.youtube.com/watch?v=T7S76L1Rkow}, year = {2013}, date = {2013-10-08}, booktitle = {Proc. of the 26th ACM Symposium on User Interface Software and Technology (UIST 2013)}, pages = { 261-270 }, abstract = {Eye gaze is a compelling interaction modality but requires a user calibration before interaction can commence. State of the art procedures require the user to fixate on a succession of calibration markers, a task that is often experienced as difficult and tedious. We present a novel approach, pursuit calibration, that instead uses moving targets for calibration. Users naturally perform smooth pursuit eye movements when they follow a moving target, and we use correlation of eye and target movement to detect the users attention and to sample data for calibration. Because the method knows when the users is attending to a target, the calibration can be performed implicitly, which enables more flexible design of the calibration task. We demonstrate this in application examples and user studies, and show that pursuit calibration is tolerant to interruption, can blend naturally with applications, and is able to calibrate users without their awareness.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Eye gaze is a compelling interaction modality but requires a user calibration before interaction can commence. State of the art procedures require the user to fixate on a succession of calibration markers, a task that is often experienced as difficult and tedious. We present a novel approach, pursuit calibration, that instead uses moving targets for calibration. Users naturally perform smooth pursuit eye movements when they follow a moving target, and we use correlation of eye and target movement to detect the users attention and to sample data for calibration. Because the method knows when the users is attending to a target, the calibration can be performed implicitly, which enables more flexible design of the calibration task. We demonstrate this in application examples and user studies, and show that pursuit calibration is tolerant to interruption, can blend naturally with applications, and is able to calibrate users without their awareness. |
 | Mélodie Vidal; Andreas Bulling; Hans Gellersen Pursuits: Spontaneous Interaction with Displays based on Smooth Pursuit Eye Movement and Moving Targets Inproceedings Proc. of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2013), pp. 439-448 , 2013. @inproceedings{vidal13_ubicomp, title = {Pursuits: Spontaneous Interaction with Displays based on Smooth Pursuit Eye Movement and Moving Targets}, author = {Mélodie Vidal and Andreas Bulling and Hans Gellersen}, url = {//dx.doi.org/10.1145/2493432.2493477 //perceptual.mpi-inf.mpg.de/files/2013/10/vidal13_ubicomp.pdf //www.youtube.com/watch?v=fpVPD_wQAWo}, year = {2013}, date = {2013-09-08}, booktitle = {Proc. of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2013)}, pages = { 439-448 }, abstract = {Although gaze is an attractive modality for pervasive interactions, the real-world implementation of eye-based interfaces poses significant challenges, such as calibration. We present Pursuits, an innovative interaction technique that enables truly spontaneous interaction with eye-based interfaces. A user can simply walk up to the screen and readily interact with moving targets. Instead of being based on gaze location, Pursuits correlates eye pursuit movements with objects dynamically moving on the interface. We evaluate the influence of target speed, number and trajectory and develop guidelines for designing Pursuits-based interfaces. We then describe six realistic usage scenarios and implement three of them to evaluate the method in a usability study and a field study. Our results show that Pursuits is a versatile and robust technique and that users can interact with Pursuits-based interfaces without prior knowledge or preparation phase.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Although gaze is an attractive modality for pervasive interactions, the real-world implementation of eye-based interfaces poses significant challenges, such as calibration. We present Pursuits, an innovative interaction technique that enables truly spontaneous interaction with eye-based interfaces. A user can simply walk up to the screen and readily interact with moving targets. Instead of being based on gaze location, Pursuits correlates eye pursuit movements with objects dynamically moving on the interface. We evaluate the influence of target speed, number and trajectory and develop guidelines for designing Pursuits-based interfaces. We then describe six realistic usage scenarios and implement three of them to evaluate the method in a usability study and a field study. Our results show that Pursuits is a versatile and robust technique and that users can interact with Pursuits-based interfaces without prior knowledge or preparation phase. |
 | Kai Kunze; Andreas Bulling; Yuzuko Utsumi; Shiga Yuki; Koichi Kise I know what you are reading -- Recognition of document types using mobile eye tracking Inproceedings Proc. of the 17th International Symposium on Wearable Computers (ISWC 2013), pp. 113-116 , ACM, New York, NY, USA, 2013, ISBN: 978-1-4503-2127-3. @inproceedings{kunze13_iswc, title = {I know what you are reading -- Recognition of document types using mobile eye tracking}, author = {Kai Kunze and Andreas Bulling and Yuzuko Utsumi and Shiga Yuki and Koichi Kise}, url = {//dx.doi.org/10.1145/2493988.2494354 //perceptual.mpi-inf.mpg.de/files/2013/10/kunze13_iswc.pdf}, isbn = {978-1-4503-2127-3}, year = {2013}, date = {2013-09-08}, booktitle = {Proc. of the 17th International Symposium on Wearable Computers (ISWC 2013)}, pages = {113-116 }, publisher = {ACM}, address = {New York, NY, USA}, abstract = {Reading is a ubiquitous activity that many people even perform in transit, such as while on the bus or while walking. Tracking reading enables us to gain more insights about expertise level and potential knowledge of users -- towards a reading log tracking and improve knowledge acquisition. As a first step towards this vision, in this work we investigate whether different document types can be automatically detected from visual behaviour recorded using a mobile eye tracker. We present an initial recognition approach that com- bines special purpose eye movement features as well as machine learning for document type detection. We evaluate our approach in a user study with eight participants and five Japanese document types and achieve a recognition performance of 74% using user-independent training.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Reading is a ubiquitous activity that many people even perform in transit, such as while on the bus or while walking. Tracking reading enables us to gain more insights about expertise level and potential knowledge of users -- towards a reading log tracking and improve knowledge acquisition. As a first step towards this vision, in this work we investigate whether different document types can be automatically detected from visual behaviour recorded using a mobile eye tracker. We present an initial recognition approach that com- bines special purpose eye movement features as well as machine learning for document type detection. We evaluate our approach in a user study with eight participants and five Japanese document types and achieve a recognition performance of 74% using user-independent training. |
 | Eduardo Velloso, Andreas Bulling; Hans Gellersen AutoBAP: Automatic Coding of Body Action and Posture Units from Wearable Sensors Inproceedings Proc. of the 5th biannual Humaine Association Conference on Affective Computing and Intelligent Interaction (ACII 2013), pp. 134-140, IEEE Computer Society, Washington, DC, USA, 2013, ISBN: 978-0-7695-5048-0. @inproceedings{velloso13_acii, title = {AutoBAP: Automatic Coding of Body Action and Posture Units from Wearable Sensors}, author = {Eduardo Velloso, Andreas Bulling and Hans Gellersen}, url = {//dx.doi.org/10.1109/ACII.2013.29 //perceptual.mpi-inf.mpg.de/files/2013/10/velloso13_acii.pdf}, isbn = {978-0-7695-5048-0}, year = {2013}, date = {2013-09-02}, booktitle = {Proc. of the 5th biannual Humaine Association Conference on Affective Computing and Intelligent Interaction (ACII 2013)}, pages = {134-140}, publisher = {IEEE Computer Society}, address = {Washington, DC, USA}, abstract = {Manual annotation of human body movement is an integral part of research on non-verbal communication and computational behaviour analysis but also a very time-consuming and tedious task. In this paper we present AutoBAP, a system that automates the coding of bodily expressions according to the body action and posture (BAP) coding scheme. Our system takes continuous body motion and gaze behaviour data as its input. The data is recorded using a full body motion tracking suit and a wearable eye tracker. From the data our system automatically generates a labelled XML file that can be visualised and edited with off-the-shelf video annotation tools. We evaluate our system in a laboratory-based user study with six participants performing scripted sequences of 184 actions. Results from the user study show that our prototype system is able to annotate 172 out of the 274 labels of the full BAP coding scheme with good agreement with a manual annotator (Cohen\'s kappa > 0.6).}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Manual annotation of human body movement is an integral part of research on non-verbal communication and computational behaviour analysis but also a very time-consuming and tedious task. In this paper we present AutoBAP, a system that automates the coding of bodily expressions according to the body action and posture (BAP) coding scheme. Our system takes continuous body motion and gaze behaviour data as its input. The data is recorded using a full body motion tracking suit and a wearable eye tracker. From the data our system automatically generates a labelled XML file that can be visualised and edited with off-the-shelf video annotation tools. We evaluate our system in a laboratory-based user study with six participants performing scripted sequences of 184 actions. Results from the user study show that our prototype system is able to annotate 172 out of the 274 labels of the full BAP coding scheme with good agreement with a manual annotator (Cohen's kappa > 0.6). |
 | Andreas Bulling; Christian Weichel; Hans Gellersen EyeContext: Recognition of High-level Contextual Cues from Human Visual Behaviour Inproceedings Proc. of the 31st SIGCHI International Conference on Human Factors in Computing Systems (CHI 2013), pp. 305-308, ACM, New York, NY, USA, 2013, ISBN: 978-1-4503-1899-0. @inproceedings{bulling13_chi, title = {EyeContext: Recognition of High-level Contextual Cues from Human Visual Behaviour}, author = {Andreas Bulling and Christian Weichel and Hans Gellersen}, url = {//dx.doi.org/10.1145/2470654.2470697 //perceptual.mpi-inf.mpg.de/files/2013/03/bulling13_chi.pdf //www.youtube.com/watch?v=bhdVmWnnnIM}, doi = {10.1145/2470654.2470697}, isbn = {978-1-4503-1899-0}, year = {2013}, date = {2013-04-27}, booktitle = {Proc. of the 31st SIGCHI International Conference on Human Factors in Computing Systems (CHI 2013)}, pages = {305-308}, publisher = {ACM}, address = {New York, NY, USA}, abstract = {In this work we present EyeContext, a system to infer high-level contextual cues from human visual behaviour. We conducted a user study to record eye movements of four participants over a full day of their daily life, totalling 42.5 hours of eye movement data. Participants were asked to self-annotate four non-mutually exclusive cues: social (interacting with somebody vs. no interaction), cognitive (concentrated work vs. leisure), physical (physically active vs. not active), and spatial (inside vs. outside a building). We evaluate a proof-of-concept EyeContext system that combines encoding of eye movements into strings and a spectrum string kernel support vector machine (SVM) classifier. Our results demonstrate the large information content available in long-term human visual behaviour and opens up new venues for research on eye-based behavioural monitoring and life logging.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } In this work we present EyeContext, a system to infer high-level contextual cues from human visual behaviour. We conducted a user study to record eye movements of four participants over a full day of their daily life, totalling 42.5 hours of eye movement data. Participants were asked to self-annotate four non-mutually exclusive cues: social (interacting with somebody vs. no interaction), cognitive (concentrated work vs. leisure), physical (physically active vs. not active), and spatial (inside vs. outside a building). We evaluate a proof-of-concept EyeContext system that combines encoding of eye movements into strings and a spectrum string kernel support vector machine (SVM) classifier. Our results demonstrate the large information content available in long-term human visual behaviour and opens up new venues for research on eye-based behavioural monitoring and life logging. |
 | Eduardo Velloso; Andreas Bulling; Hans Gellersen MotionMA: Motion Modelling and Analysis by Demonstration Inproceedings Proc. of the 31st SIGCHI International Conference on Human Factors in Computing Systems (CHI 2013), pp. 1309-1318, ACM, New York, NY, USA, 2013, ISBN: 978-1-4503-1899-0. @inproceedings{velloso13_chi, title = {MotionMA: Motion Modelling and Analysis by Demonstration}, author = {Eduardo Velloso and Andreas Bulling and Hans Gellersen}, url = {//dx.doi.org/10.1145/2470654.2466171 //perceptual.mpi-inf.mpg.de/files/2013/03/velloso13_chi.pdf //www.youtube.com/watch?v=fFFWyt9LOhg}, isbn = {978-1-4503-1899-0}, year = {2013}, date = {2013-04-27}, booktitle = {Proc. of the 31st SIGCHI International Conference on Human Factors in Computing Systems (CHI 2013)}, pages = {1309-1318}, publisher = {ACM}, address = {New York, NY, USA}, abstract = {Particularly in sports or physical rehabilitation, users have to perform body movements in a specific manner for the exercises to be most effective. It remains a challenge for experts to specify how to perform such movements so that an automated system can analyse further performances of it. In a user study with 10 participants we show that experts' explicit estimates do not correspond to their performances. To address this issue we present MotionMA, a system that: (1) automatically extracts a model of movements demonstrated by one user, e.g. a trainer, (2) assesses the performance of other users repeating this movement in real time, and (3) provides real-time feedback on how to improve their performance. We evaluated the system in a second study in which 10 other participants used the system to demonstrate arbitrary movements. Our results demonstrate that MotionMA is able to extract an accurate movement model to spot mistakes and variations in movement execution.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Particularly in sports or physical rehabilitation, users have to perform body movements in a specific manner for the exercises to be most effective. It remains a challenge for experts to specify how to perform such movements so that an automated system can analyse further performances of it. In a user study with 10 participants we show that experts' explicit estimates do not correspond to their performances. To address this issue we present MotionMA, a system that: (1) automatically extracts a model of movements demonstrated by one user, e.g. a trainer, (2) assesses the performance of other users repeating this movement in real time, and (3) provides real-time feedback on how to improve their performance. We evaluated the system in a second study in which 10 other participants used the system to demonstrate arbitrary movements. Our results demonstrate that MotionMA is able to extract an accurate movement model to spot mistakes and variations in movement execution. |
 | Yanxia Zhang; Andreas Bulling; Hans Gellersen SideWays: A Gaze Interface for Spontaneous Interaction with Situated Displays Inproceedings Proc. of the 31st SIGCHI International Conference on Human Factors in Computing Systems (CHI 2013), pp. 851-860, ACM, New York, NY, USA, 2013, ISBN: 978-1-4503-1899-0. @inproceedings{zhang13_chi, title = {SideWays: A Gaze Interface for Spontaneous Interaction with Situated Displays}, author = {Yanxia Zhang and Andreas Bulling and Hans Gellersen}, url = {//dx.doi.org/10.1145/2470654.2470775 //perceptual.mpi-inf.mpg.de/files/2013/03/zhang13_chi.pdf //www.youtube.com/watch?v=cucOArVoyV0}, isbn = {978-1-4503-1899-0}, year = {2013}, date = {2013-04-27}, booktitle = {Proc. of the 31st SIGCHI International Conference on Human Factors in Computing Systems (CHI 2013)}, pages = {851-860}, publisher = {ACM}, address = {New York, NY, USA}, abstract = {Eye gaze is compelling for interaction with situated displays as we naturally use our eyes to engage with them. In this work we present SideWays, a novel person-independent eye gaze interface that supports spontaneous interaction with displays: users can just walk up to a display and immediately interact using their eyes, without any prior user calibration or training. Requiring only a single off-the-shelf camera and lightweight image processing, SideWays robustly detects whether users attend to the centre of the display or cast glances to the left or right. The system supports an interaction model in which attention to the central display is the default state, while "sidelong glances" trigger input or actions. The robustness of the system and usability of the interaction model are validated in a study with 14 participants. Analysis of the participants' strategies in performing different tasks provides insights on gaze control strategies for design of SideWays applications.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Eye gaze is compelling for interaction with situated displays as we naturally use our eyes to engage with them. In this work we present SideWays, a novel person-independent eye gaze interface that supports spontaneous interaction with displays: users can just walk up to a display and immediately interact using their eyes, without any prior user calibration or training. Requiring only a single off-the-shelf camera and lightweight image processing, SideWays robustly detects whether users attend to the centre of the display or cast glances to the left or right. The system supports an interaction model in which attention to the central display is the default state, while "sidelong glances" trigger input or actions. The robustness of the system and usability of the interaction model are validated in a study with 14 participants. Analysis of the participants' strategies in performing different tasks provides insights on gaze control strategies for design of SideWays applications. |
 | Mélodie Vidal; Ken Pfeuffer; Andreas Bulling; Hans Gellersen Pursuits: Eye-based Interaction with Moving Targets Inproceedings Ext. Abstr. of the 31st SIGCHI International Conference on Human Factors in Computing Systems (CHI 2013), pp. 3147–3150, ACM, Paris, France, 2013, ISBN: 978-1-4503-1952-2. @inproceedings{vidal13_chi, title = {Pursuits: Eye-based Interaction with Moving Targets}, author = {Mélodie Vidal and Ken Pfeuffer and Andreas Bulling and Hans Gellersen}, url = {//dx.doi.org/10.1145/2468356.2479632 //perceptual.mpi-inf.mpg.de/files/2013/10/vidal13_chi.pdf //www.youtube.com/watch?v=oppQXm4uaXo}, isbn = {978-1-4503-1952-2}, year = {2013}, date = {2013-04-27}, booktitle = {Ext. Abstr. of the 31st SIGCHI International Conference on Human Factors in Computing Systems (CHI 2013)}, pages = {3147--3150}, publisher = {ACM}, address = {Paris, France}, abstract = {Eye-based interaction has commonly been based on estimation of eye gaze direction, to locate objects for interaction. We introduce Pursuits, a novel and very different eye tracking method that instead is based on following the trajectory of eye movement and comparing this with trajectories of objects in the field of view. Because the eyes naturally follow the trajectory of moving objects of interest, our method is able to detect what the user is looking at, by matching eye movement and object movement. We illustrate Pursuits with three applications that demonstrate how the method facilitates natural interaction with moving targets.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Eye-based interaction has commonly been based on estimation of eye gaze direction, to locate objects for interaction. We introduce Pursuits, a novel and very different eye tracking method that instead is based on following the trajectory of eye movement and comparing this with trajectories of objects in the field of view. Because the eyes naturally follow the trajectory of moving objects of interest, our method is able to detect what the user is looking at, by matching eye movement and object movement. We illustrate Pursuits with three applications that demonstrate how the method facilitates natural interaction with moving targets. |
 | Eduardo Velloso; Andreas Bulling; Hans Gellersen; Wallace Ugulino; Hugo Fuks Qualitative Activity Recognition of Weight Lifting Exercises Inproceedings Proc. of the 4th Augmented Human International Conference (AH 2013), pp. 116-123 , ACM, New York, NY, USA, 2013, ISBN: 978-1-4503-1904-1. @inproceedings{ah13_velloso, title = {Qualitative Activity Recognition of Weight Lifting Exercises}, author = {Eduardo Velloso and Andreas Bulling and Hans Gellersen and Wallace Ugulino and Hugo Fuks}, url = {//dx.doi.org/10.1145/2459236.2459256 //perceptual.mpi-inf.mpg.de/files/2013/03/velloso13_ah.pdf}, isbn = { 978-1-4503-1904-1}, year = {2013}, date = {2013-03-07}, booktitle = {Proc. of the 4th Augmented Human International Conference (AH 2013)}, pages = {116-123 }, publisher = {ACM}, address = {New York, NY, USA}, abstract = {Research on human activity recognition has traditionally focused on discriminating between different activities, i.e. to predict ``which\'\' activity was performed at a specific point in time. The quality of executing an activity, the ``how (well)\'\', has only received little attention so far, even though it potentially provides useful information for a large variety of applications, such as sports training. In this work we first define quality of execution and investigate three aspects that pertain to qualitative activity recognition: the problem of specifying correct execution, the automatic and robust detection of execution mistakes, and how to provide feedback on the quality of execution to the user. We illustrate our approach on the example problem of qualitatively assessing and providing feedback on weight lifting exercises. In two user studies we try out a sensor- and a model-based approach to qualitative activity recognition. Our results underline the potential of model-based assessment and the positive impact of real-time user feedback on the quality of execution.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Research on human activity recognition has traditionally focused on discriminating between different activities, i.e. to predict ``which'' activity was performed at a specific point in time. The quality of executing an activity, the ``how (well)'', has only received little attention so far, even though it potentially provides useful information for a large variety of applications, such as sports training. In this work we first define quality of execution and investigate three aspects that pertain to qualitative activity recognition: the problem of specifying correct execution, the automatic and robust detection of execution mistakes, and how to provide feedback on the quality of execution to the user. We illustrate our approach on the example problem of qualitatively assessing and providing feedback on weight lifting exercises. In two user studies we try out a sensor- and a model-based approach to qualitative activity recognition. Our results underline the potential of model-based assessment and the positive impact of real-time user feedback on the quality of execution. |
 | Jayson Turner; Jason Alexander; Andreas Bulling; Dominik Schmidt; Hans Gellersen Eye Pull, Eye Push: Moving Objects between Large Screens and Personal Devices with Gaze & Touch Inproceedings Proc. of the 14th IFIP TC13 Conference on Human-Computer Interaction (INTERACT 2013), 2013. @inproceedings{turner13_interact, title = {Eye Pull, Eye Push: Moving Objects between Large Screens and Personal Devices with Gaze & Touch}, author = {Jayson Turner and Jason Alexander and Andreas Bulling and Dominik Schmidt and Hans Gellersen}, url = {//perceptual.mpi-inf.mpg.de/files/2013/10/turner13_interact.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {Proc. of the 14th IFIP TC13 Conference on Human-Computer Interaction (INTERACT 2013)}, abstract = {Previous work has validated the eyes and mobile input as a viable approach for pointing at, and selecting out of reach objects. This work presents Eye Pull, Eye Push, a novel interaction concept for content transfer between public and personal devices using gaze and touch. We present three techniques that enable this interaction: Eye Cut & Paste, Eye Drag & Drop, and Eye Summon & Cast. We outline and discuss several scenarios in which these techniques can be used. In a user study we found that participants responded well to the visual feedback provided by Eye Drag & Drop during object movement. In contrast, we found that although Eye Summon & Cast significantly improved performance, participants had difficulty coordinating their hands and eyes during interaction.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Previous work has validated the eyes and mobile input as a viable approach for pointing at, and selecting out of reach objects. This work presents Eye Pull, Eye Push, a novel interaction concept for content transfer between public and personal devices using gaze and touch. We present three techniques that enable this interaction: Eye Cut & Paste, Eye Drag & Drop, and Eye Summon & Cast. We outline and discuss several scenarios in which these techniques can be used. In a user study we found that participants responded well to the visual feedback provided by Eye Drag & Drop during object movement. In contrast, we found that although Eye Summon & Cast significantly improved performance, participants had difficulty coordinating their hands and eyes during interaction. |
 | Sabrina Hoppe; Florian Daiber; Markus Löchtefeld Eype - Using Eye-Traces for Eye-Typing Inproceedings Workshop on Grand Challenges in Text Entry. ACM International Conference on Human Factors in Computing Systems (CHI 13), ACM, 2013. @inproceedings{hoppe_chi13, title = {Eype - Using Eye-Traces for Eye-Typing}, author = {Sabrina Hoppe and Florian Daiber and Markus Löchtefeld }, url = {//prezi.com/l4pv2mzl5lfy/eype/ //www.dfki.de/web/forschung/publikationen?pubid=6817 //perceptual.mpi-inf.mpg.de/files/2015/03/eype.pdf}, year = {2013}, date = {2013-01-01}, booktitle = { Workshop on Grand Challenges in Text Entry. ACM International Conference on Human Factors in Computing Systems (CHI 13)}, publisher = {ACM}, abstract = {Current eye-typing systems are suffering from the needed dwell timeout which limits the possible entry rate. In this position paper we discuss how the usage of eye-traces on on-screen keyboards could be used for almost dwell timeout free gaze based communication. This could significantly increase the entry rate of eye-typing systems.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Current eye-typing systems are suffering from the needed dwell timeout which limits the possible entry rate. In this position paper we discuss how the usage of eye-traces on on-screen keyboards could be used for almost dwell timeout free gaze based communication. This could significantly increase the entry rate of eye-typing systems. |
 | Junjie Yan; Xucong Zhang; Zhen Lei; Shengcai Liao; Stan Z Li Robust multi-resolution pedestrian detection in traffic scenes Inproceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2013, pp. 3033–3040, IEEE 2013. @inproceedings{yan2013robust, title = {Robust multi-resolution pedestrian detection in traffic scenes}, author = {Junjie Yan and Xucong Zhang and Zhen Lei and Shengcai Liao and Stan Z Li}, url = {//perceptual.mpi-inf.mpg.de/files/2015/03/Yan_CVPR13.pdf}, year = {2013}, date = {2013-01-01}, booktitle = { IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2013}, pages = {3033--3040}, organization = {IEEE}, abstract = {The serious performance decline with decreasing resolution is the major bottleneck for current pedestrian detection techniques. In this paper, we take pedestrian detection in different resolutions as different but related problems, and propose a Multi-Task model to jointly consider their commonness and differences. The model contains resolution aware transformations to map pedestrians in different resolutions to a common space, where a shared detector is constructed to distinguish pedestrians from background. For model learning, we present a coordinate descent procedure to learn the resolution aware transformations and deformable part model (DPM) based detector iteratively. In traffic scenes, there are many false positives located around vehicles, therefore, we further build a context model to suppress them according to the pedestrian-vehicle relationship. The context model can be learned automatically even when the vehicle annotations are not available. Our method reduces the mean miss rate to 60% for pedestrians taller than 30 pixels on the Caltech Pedestrian Benchmark, which noticeably outperforms previous state-of-the-art (71%).}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } The serious performance decline with decreasing resolution is the major bottleneck for current pedestrian detection techniques. In this paper, we take pedestrian detection in different resolutions as different but related problems, and propose a Multi-Task model to jointly consider their commonness and differences. The model contains resolution aware transformations to map pedestrians in different resolutions to a common space, where a shared detector is constructed to distinguish pedestrians from background. For model learning, we present a coordinate descent procedure to learn the resolution aware transformations and deformable part model (DPM) based detector iteratively. In traffic scenes, there are many false positives located around vehicles, therefore, we further build a context model to suppress them according to the pedestrian-vehicle relationship. The context model can be learned automatically even when the vehicle annotations are not available. Our method reduces the mean miss rate to 60% for pedestrians taller than 30 pixels on the Caltech Pedestrian Benchmark, which noticeably outperforms previous state-of-the-art (71%). |
 | Junjie Yan; Xucong Zhang; Zhen Lei; Stan Z. Li Real-time high performance deformable model for face detection in the wild Inproceedings International Conference on Biometrics (ICB), pp. 1–6, IEEE 2013. @inproceedings{yan2013real, title = {Real-time high performance deformable model for face detection in the wild}, author = { Junjie Yan and Xucong Zhang and Zhen Lei and Stan Z. Li}, url = {//perceptual.mpi-inf.mpg.de/files/2015/03/Yan_Vis13.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {International Conference on Biometrics (ICB)}, pages = {1--6}, organization = {IEEE}, abstract = {We present an effective deformable part model for face detection in the wild. Compared with previous systems on face detection, there are mainly three contributions. The first is an efficient method for calculating histogram of oriented gradients by pre-calculated lookup tables, which only has read and write memory operations and the feature pyramid can be calculated in real-time. The second is a Sparse Constrained Latent Bilinear Model to simultaneously learn the discriminative deformable part model, and reduce the feature dimension by sparse transformations for efficient inference. The third contribution is a deformable part based cascade, where every stage is a deformable part in the discriminatively learned model. By integrating the three techniques, we demonstrate noticeable improvements over previous state-of-the-art on FDDB with real-time speed, under widely comparisons with both academic and commercial detectors.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } We present an effective deformable part model for face detection in the wild. Compared with previous systems on face detection, there are mainly three contributions. The first is an efficient method for calculating histogram of oriented gradients by pre-calculated lookup tables, which only has read and write memory operations and the feature pyramid can be calculated in real-time. The second is a Sparse Constrained Latent Bilinear Model to simultaneously learn the discriminative deformable part model, and reduce the feature dimension by sparse transformations for efficient inference. The third contribution is a deformable part based cascade, where every stage is a deformable part in the discriminatively learned model. By integrating the three techniques, we demonstrate noticeable improvements over previous state-of-the-art on FDDB with real-time speed, under widely comparisons with both academic and commercial detectors. |
 | Xucong Zhang; Xiaoyun Wang; Yingmin Jia The Visual Internet of Things System Based on Depth Camera Inproceedings Proceedings of the Chinese Intelligent Automation Conference, pp. 447–455, Springer 2013. @inproceedings{zhang2013visual, title = {The Visual Internet of Things System Based on Depth Camera}, author = {Xucong Zhang and Xiaoyun Wang and Yingmin Jia}, url = {//perceptual.mpi-inf.mpg.de/files/2015/03/Zhang_ICB13.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {Proceedings of the Chinese Intelligent Automation Conference}, pages = {447--455}, organization = {Springer}, abstract = {The Visual Internet of Things is an important part of information technology. It is proposed to strength the system with atomic visual label by taking visual camera as the sensor. Unfortunately, the traditional color camera is greatly influenced by the condition of illumination, and suffers from the low detection accuracy. To solve that problem, we build a new Visual Internet of Things with depth camera. The new system takes advantage of the illumination invariant of depth information and rich texture of color information to label the objects in the scene. We use Kinect as the sensor to get the color and depth information of the scene, modify the traditional computer vision technology for the combinatorial information to label target object, and return the result to user interface. We set up the hardware platform and the real application validates the robust and high precision of the system. }, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } The Visual Internet of Things is an important part of information technology. It is proposed to strength the system with atomic visual label by taking visual camera as the sensor. Unfortunately, the traditional color camera is greatly influenced by the condition of illumination, and suffers from the low detection accuracy. To solve that problem, we build a new Visual Internet of Things with depth camera. The new system takes advantage of the illumination invariant of depth information and rich texture of color information to label the objects in the scene. We use Kinect as the sensor to get the color and depth information of the scene, modify the traditional computer vision technology for the combinatorial information to label target object, and return the result to user interface. We set up the hardware platform and the real application validates the robust and high precision of the system. |
 | Junjie Yan; Xucong Zhang; Zhen Lei; Stan Z. Li Structural face detection Inproceedings 10th Automatic Face and Gesture Recognition (FG), 2013. @inproceedings{Yan_FG13, title = {Structural face detection}, author = {Junjie Yan and Xucong Zhang and Zhen Lei and Stan Z. Li}, url = {//perceptual.mpi-inf.mpg.de/files/2015/03/yan_FG2013.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {10th Automatic Face and Gesture Recognition (FG)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
book chapters
 | Daniel Roggen; Andreas Bulling; Gerhard Tröster Signal processing technologies for activity-aware smart textiles Book Chapter Kirstein, Tünde (Ed.): (139), Chapter 12, pp. 329-366, Woodhead Publishing Limited, 2013, ISBN: 0 85709 342 8. @inbook{roggen13_wpt, title = {Signal processing technologies for activity-aware smart textiles}, author = {Daniel Roggen and Andreas Bulling and Gerhard Tröster}, editor = {Tünde Kirstein}, url = {//www.woodheadpublishing.com/en/book.aspx?bookID=2518}, isbn = {0 85709 342 8}, year = {2013}, date = {2013-01-01}, number = {139}, pages = {329-366}, publisher = {Woodhead Publishing Limited}, chapter = {12}, series = {Woodhead Publishing Series in Textiles}, abstract = {Garments made of smart textiles have an enormous potential for embedding sensors in close proximity to the body in an unobtrusive and comfortable manner. Combined with signal processing and pattern recognition technologies, complex high-level information about human behaviors or situations can be inferred from the sensor data. The goal of this chapter is to introduce the reader to the design of activity-aware systems that use body-worn sensors, such as those that can be made available through smart textiles. We start this chapter by emphasizing recent trends towards ‘wearable’ sensing and computing and we present several examples of activity-aware applications. Then we outline the role that smart textiles can play in activity-aware applications, but also the challenges that they pose. We conclude by discussing the design process followed to devise activity-aware systems: the choice of sensors, the available data processing methods, and the evaluation techniques. We discuss recent data processing methods that address the challenges resulting from the use of smart textiles.}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } Garments made of smart textiles have an enormous potential for embedding sensors in close proximity to the body in an unobtrusive and comfortable manner. Combined with signal processing and pattern recognition technologies, complex high-level information about human behaviors or situations can be inferred from the sensor data. The goal of this chapter is to introduce the reader to the design of activity-aware systems that use body-worn sensors, such as those that can be made available through smart textiles. We start this chapter by emphasizing recent trends towards ‘wearable’ sensing and computing and we present several examples of activity-aware applications. Then we outline the role that smart textiles can play in activity-aware applications, but also the challenges that they pose. We conclude by discussing the design process followed to devise activity-aware systems: the choice of sensors, the available data processing methods, and the evaluation techniques. We discuss recent data processing methods that address the challenges resulting from the use of smart textiles. |
 | Albrecht Schmidt; Andreas Bulling; Christian Holz Proc. 4th Augmented Human International Conference (AH) Book Chapter ACM, Stuttgart, Germany, 2013, ISBN: 978-1-4503-1904-1. @inbook{schmidt13_ah, title = {Proc. 4th Augmented Human International Conference (AH)}, author = {Albrecht Schmidt and Andreas Bulling and Christian Holz}, isbn = {978-1-4503-1904-1}, year = {2013}, date = {2013-01-01}, publisher = {ACM}, address = {Stuttgart, Germany}, abstract = {We are very happy to present the proceedings of the 4th Augmented Human International Conference (Augmented Human 2013). Augmented Human 2013 focuses on augmenting human capabilities through technology for increased well-being and enjoyable human experience. The conference is in cooperation with ACM SIGCHI, with its proceedings to be archived in ACM's Digital Library. With technological advances, computing has progressively moved beyond the desktop into new physical and social contexts. As physical artifacts gain new computational behaviors, they become reprogrammable, customizable, repurposable, and interoperable in rich ecologies and diverse contexts. They also become more complex, and require intense design effort in order to be functional, usable, and enjoyable. Designing such systems requires interdisciplinary thinking. Their creation must not only encompass software, electronics, and mechanics, but also the system's physical form and behavior, its social and physical milieu, and beyond.}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } We are very happy to present the proceedings of the 4th Augmented Human International Conference (Augmented Human 2013). Augmented Human 2013 focuses on augmenting human capabilities through technology for increased well-being and enjoyable human experience. The conference is in cooperation with ACM SIGCHI, with its proceedings to be archived in ACM's Digital Library. With technological advances, computing has progressively moved beyond the desktop into new physical and social contexts. As physical artifacts gain new computational behaviors, they become reprogrammable, customizable, repurposable, and interoperable in rich ecologies and diverse contexts. They also become more complex, and require intense design effort in order to be functional, usable, and enjoyable. Designing such systems requires interdisciplinary thinking. Their creation must not only encompass software, electronics, and mechanics, but also the system's physical form and behavior, its social and physical milieu, and beyond. |
Andreas Bulling; Roman Bednarik Proc. 3rd International Workshop on Pervasive Eye Tracking and Mobile Eye-Based Interaction (PETMEI) Book Chapter Proc. 17th European Conference on Eye Movements (ECEM), 2013. @inbook{bulling13_petmei, title = {Proc. 3rd International Workshop on Pervasive Eye Tracking and Mobile Eye-Based Interaction (PETMEI)}, author = { Andreas Bulling and Roman Bednarik}, year = {2013}, date = {2013-01-01}, booktitle = {Proc. 17th European Conference on Eye Movements (ECEM)}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } |
