journal articles
 | Sandra Dörrenbächer; Philipp Müller; Johannes Tröger; Jutta Kray Dissociable effects of game elements on motivation and cognition in a task-switching training in middle childhood Journal Article Frontiers in Psychology, 5 (1275), 2014. @article{Doerrenbaecher14_fronPsy, title = {Dissociable effects of game elements on motivation and cognition in a task-switching training in middle childhood}, author = {Sandra Dörrenbächer and Philipp Müller and Johannes Tröger and Jutta Kray}, url = {//www.ncbi.nlm.nih.gov/pmc/articles/PMC4230167/ //perceptual.mpi-inf.mpg.de/files/2014/11/doerrenbaecher_fPsy14.pdf}, doi = {10.3389/fpsyg.2014.01275}, year = {2014}, date = {2014-11-13}, journal = {Frontiers in Psychology}, volume = {5}, number = {1275}, abstract = {Although motivational reinforcers are often used to enhance the attractiveness of trainings of cognitive control in children, little is known about how such motivational manipulations of the setting contribute to separate gains in motivation and cognitive-control performance. Here we provide a framework for systematically investigating the impact of a motivational video-game setting on the training motivation, the task performance, and the transfer success in a task-switching training in middle-aged children (8–11 years of age). We manipulated both the type of training (low-demanding/single-task training vs. high-demanding/task-switching training) as well as the motivational setting (low-motivational/without video-game elements vs. high-motivational/with video-game elements) separately from another. The results indicated that the addition of game elements to a training setting enhanced the intrinsic interest in task practice, independently of the cognitive demands placed by the training type. In the task-switching group, the high-motivational training setting led to an additional enhancement of task and switching performance during the training phase right from the outset. These motivation-induced benefits projected onto the switching performance in a switching situation different from the trained one (near-transfer measurement). However, in structurally dissimilar cognitive tasks (far-transfer measurement), the motivational gains only transferred to the response dynamics (speed of processing). Hence, the motivational setting clearly had a positive impact on the training motivation and on the paradigm-specific task-switching abilities; it did not, however, consistently generalize on broad cognitive processes. These findings shed new light on the conflation of motivation and cognition in childhood and may help to refine guidelines for designing adequate training interventions.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Although motivational reinforcers are often used to enhance the attractiveness of trainings of cognitive control in children, little is known about how such motivational manipulations of the setting contribute to separate gains in motivation and cognitive-control performance. Here we provide a framework for systematically investigating the impact of a motivational video-game setting on the training motivation, the task performance, and the transfer success in a task-switching training in middle-aged children (8–11 years of age). We manipulated both the type of training (low-demanding/single-task training vs. high-demanding/task-switching training) as well as the motivational setting (low-motivational/without video-game elements vs. high-motivational/with video-game elements) separately from another. The results indicated that the addition of game elements to a training setting enhanced the intrinsic interest in task practice, independently of the cognitive demands placed by the training type. In the task-switching group, the high-motivational training setting led to an additional enhancement of task and switching performance during the training phase right from the outset. These motivation-induced benefits projected onto the switching performance in a switching situation different from the trained one (near-transfer measurement). However, in structurally dissimilar cognitive tasks (far-transfer measurement), the motivational gains only transferred to the response dynamics (speed of processing). Hence, the motivational setting clearly had a positive impact on the training motivation and on the paradigm-specific task-switching abilities; it did not, however, consistently generalize on broad cognitive processes. These findings shed new light on the conflation of motivation and cognition in childhood and may help to refine guidelines for designing adequate training interventions. |
Dirk Wentura; Philipp Müller; Klaus Rothermund Attentional capture by evaluative stimuli: Gain- and loss-connoting colors boost the additional-singleton effect Journal Article Psychonomic Bulletin & Review, 21 (3), pp. 701-707, 2014, ISSN: 1069-9384. @article{Wentura14_PsyBull, title = {Attentional capture by evaluative stimuli: Gain- and loss-connoting colors boost the additional-singleton effect}, author = {Dirk Wentura and Philipp Müller and Klaus Rothermund}, url = {//link.springer.com/article/10.3758/s13423-013-0531-z}, doi = {10.3758/s13423-013-0531-z}, issn = {1069-9384}, year = {2014}, date = {2014-06-01}, journal = {Psychonomic Bulletin & Review}, volume = {21}, number = {3}, pages = {701-707}, abstract = {In a valence induction task, one color acquired positive valence by indicating the chance to win money (in the case of fast and correct responses), and a different color acquired negative valence by indicating the danger to lose money (in the case of slow or incorrect responses). In the additional-singleton trials of a visual search task, the task-irrelevant singleton color was either the positive one, the negative one, or one of two neutral colors. We found an additional-singleton effect (i.e., longer RTs with a singleton color than in the no-singleton control condition). This effect was significantly increased for the two valent colors (with no differences between them) relative to the two neutral colors (with no differences between them, either). This result favors the hypothesis that the general relevance of stimuli elicits attentional capture, rather than the negativity bias hypothesis.}, keywords = {}, pubstate = {published}, tppubtype = {article} } In a valence induction task, one color acquired positive valence by indicating the chance to win money (in the case of fast and correct responses), and a different color acquired negative valence by indicating the danger to lose money (in the case of slow or incorrect responses). In the additional-singleton trials of a visual search task, the task-irrelevant singleton color was either the positive one, the negative one, or one of two neutral colors. We found an additional-singleton effect (i.e., longer RTs with a singleton color than in the no-singleton control condition). This effect was significantly increased for the two valent colors (with no differences between them) relative to the two neutral colors (with no differences between them, either). This result favors the hypothesis that the general relevance of stimuli elicits attentional capture, rather than the negativity bias hypothesis. | |
 | Andreas Bulling; Ulf Blanke; Bernt Schiele A Tutorial on Human Activity Recognition Using Body-worn Inertial Sensors Journal Article ACM Computing Surveys, 46 (3), pp. 33:1-33:33, 2014. @article{bulling14_csur, title = {A Tutorial on Human Activity Recognition Using Body-worn Inertial Sensors}, author = { Andreas Bulling and Ulf Blanke and Bernt Schiele}, url = {//github.com/andyknownasabu/ActRecTut //dx.doi.org/10.1145/2499621 //perceptual.mpi-inf.mpg.de/files/2015/08/bulling14_csur.pdf}, year = {2014}, date = {2014-01-01}, journal = {ACM Computing Surveys}, volume = {46}, number = {3}, pages = {33:1-33:33}, abstract = {The last 20 years have seen an ever increasing research activity in the field of human activity recognition. With activity recognition having considerably matured so did the number of challenges in designing, implementing and evaluating activity recognition systems. This tutorial aims to provide a comprehensive hands-on introduction for newcomers to the field of human activity recognition. It specifically focuses on activity recognition using on-body inertial sensors. We first discuss the key research challenges that human activity recognition shares with general pattern recognition and identify those challenges that are specific to human activity recognition. We then describe the concept of an activity recognition chain (ARC) as a general-purpose framework for designing and evaluating activity recognition systems. We detail each component of the framework, provide references to related research and introduce the best practise methods developed by the activity recognition research community. We conclude with the educational example problem of recognising different hand gestures from inertial sensors attached to the upper and lower arm. We illustrate how each component of this framework can be implemented for this specific activity recognition problem and demonstrate how different implementations compare and how they impact overall recognition performance.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The last 20 years have seen an ever increasing research activity in the field of human activity recognition. With activity recognition having considerably matured so did the number of challenges in designing, implementing and evaluating activity recognition systems. This tutorial aims to provide a comprehensive hands-on introduction for newcomers to the field of human activity recognition. It specifically focuses on activity recognition using on-body inertial sensors. We first discuss the key research challenges that human activity recognition shares with general pattern recognition and identify those challenges that are specific to human activity recognition. We then describe the concept of an activity recognition chain (ARC) as a general-purpose framework for designing and evaluating activity recognition systems. We detail each component of the framework, provide references to related research and introduce the best practise methods developed by the activity recognition research community. We conclude with the educational example problem of recognising different hand gestures from inertial sensors attached to the upper and lower arm. We illustrate how each component of this framework can be implemented for this specific activity recognition problem and demonstrate how different implementations compare and how they impact overall recognition performance. |
 | Andreas Bulling; Thorsten O. Zander Cognition-Aware Computing Journal Article IEEE Pervasive Computing, 13 (3), pp. 80-83, 2014. @article{bulling14_pcm, title = {Cognition-Aware Computing}, author = { Andreas Bulling and Thorsten O. Zander}, url = {//dx.doi.org/10.1109/mprv.2014.42 //perceptual.mpi-inf.mpg.de/files/2014/10/bulling14_pervasive.pdf}, year = {2014}, date = {2014-01-01}, journal = {IEEE Pervasive Computing}, volume = {13}, number = {3}, pages = {80-83}, abstract = {Despite significant advances in context sensing and inference since its inception in the late 1990s, context-aware computing still doesn't implement a holistic view of all covert aspects of the user state. Here, the authors introduce the concept of cognitive context as an extension to the current notion of context with a cognitive dimension. They argue that visual behavior and brain activity are two promising sensing modalities for assessing the cognitive context and thus the development of cognition-aware computing systems.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Despite significant advances in context sensing and inference since its inception in the late 1990s, context-aware computing still doesn't implement a holistic view of all covert aspects of the user state. Here, the authors introduce the concept of cognitive context as an extension to the current notion of context with a cognitive dimension. They argue that visual behavior and brain activity are two promising sensing modalities for assessing the cognitive context and thus the development of cognition-aware computing systems. |
conference papers
 | Yanxia Zhang; Hans Jörg Müller; Ming Ki Chong; Andreas Bulling; Hans Gellersen GazeHorizon: Enabling Passers-by to Interact with Public Displays by Gaze Inproceedings Proc. of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2014), pp. 559-563, 2014. @inproceedings{zhang14_ubicomp, title = {GazeHorizon: Enabling Passers-by to Interact with Public Displays by Gaze}, author = { Yanxia Zhang and Hans Jörg Müller and Ming Ki Chong and Andreas Bulling and Hans Gellersen}, url = {//dx.doi.org/10.1145/2632048.2636071 //perceptual.mpi-inf.mpg.de/files/2014/09/p559-zhang.pdf //www.youtube.com/watch?v=zKsSeLvvsXU}, year = {2014}, date = {2014-09-13}, booktitle = {Proc. of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2014)}, pages = {559-563}, abstract = {Public displays can be made interactive by adding gaze control. However, gaze interfaces do not offer any physical affordance, and require users to move into a tracking range. We present GazeHorizon, a system that provides interactive assistance to enable passers-by to walk up to a display and to navigate content using their eyes only. The system was developed through field studies culminating in a four-day deployment in a public environment. Our results show that novice users can be facilitated to successfully use gaze control by making them aware of the interface at first glance and guiding them interactively into the tracking range.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Public displays can be made interactive by adding gaze control. However, gaze interfaces do not offer any physical affordance, and require users to move into a tracking range. We present GazeHorizon, a system that provides interactive assistance to enable passers-by to walk up to a display and to navigate content using their eyes only. The system was developed through field studies culminating in a four-day deployment in a public environment. Our results show that novice users can be facilitated to successfully use gaze control by making them aware of the interface at first glance and guiding them interactively into the tracking range. |
 | Stefan Schneegass; Frank Steimle; Andreas Bulling; Florian Alt; Albrecht Schmidt SmudgeSafe: Geometric Image Transformations for Smudge-resistant User Authentication Inproceedings Proc. of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2014), pp. 775-786, 2014. @inproceedings{schneegass14_ubicomp, title = {SmudgeSafe: Geometric Image Transformations for Smudge-resistant User Authentication}, author = { Stefan Schneegass and Frank Steimle and Andreas Bulling and Florian Alt and Albrecht Schmidt}, url = {//perceptual.mpi-inf.mpg.de/files/2014/09/p775-schneegass.pdf //dx.doi.org/10.1145/2632048.2636090}, year = {2014}, date = {2014-09-13}, booktitle = {Proc. of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2014)}, pages = { 775-786}, abstract = {Touch-enabled user interfaces have become ubiquitous, such as on ATMs or portable devices. At the same time, authentication using touch input is problematic, since finger smudge traces may allow attackers to reconstruct passwords. We present SmudgeSafe, an authentication system that uses random geometric image transformations, such as translation, rotation, scaling, shearing, and flipping, to increase the security of cued-recall graphical passwords. We describe the design space of these transformations and report on two user studies: A lab-based security study involving 20 participants in attacking user-defined passwords, using high quality pictures of real smudge traces captured on a mobile phone display; and an in-the-field usability study with 374 participants who generated more than 130,000 logins on a mobile phone implementation of SmudgeSafe. Results show that SmudgeSafe significantly increases security compared to authentication schemes based on PINs and lock patterns, and exhibits very high learnability, efficiency, and memorability.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Touch-enabled user interfaces have become ubiquitous, such as on ATMs or portable devices. At the same time, authentication using touch input is problematic, since finger smudge traces may allow attackers to reconstruct passwords. We present SmudgeSafe, an authentication system that uses random geometric image transformations, such as translation, rotation, scaling, shearing, and flipping, to increase the security of cued-recall graphical passwords. We describe the design space of these transformations and report on two user studies: A lab-based security study involving 20 participants in attacking user-defined passwords, using high quality pictures of real smudge traces captured on a mobile phone display; and an in-the-field usability study with 374 participants who generated more than 130,000 logins on a mobile phone implementation of SmudgeSafe. Results show that SmudgeSafe significantly increases security compared to authentication schemes based on PINs and lock patterns, and exhibits very high learnability, efficiency, and memorability. |
 | Moritz Kassner; William Patera; Andreas Bulling Pupil: an open source platform for pervasive eye tracking and mobile gaze-based interaction Inproceedings Adj. Proc. of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2014), pp. 1151-1160 , 2014. @inproceedings{Kassner14_ubicomp, title = {Pupil: an open source platform for pervasive eye tracking and mobile gaze-based interaction}, author = {Moritz Kassner and William Patera and Andreas Bulling}, url = {//perceptual.mpi-inf.mpg.de/files/2014/09/p1151-kassner.pdf}, doi = {10.1145/2638728.2641695}, year = {2014}, date = {2014-09-13}, booktitle = {Adj. Proc. of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2014)}, pages = {1151-1160 }, abstract = {In this paper we present Pupil -- an accessible, affordable, and extensible open source platform for pervasive eye tracking and gaze-based interaction. Pupil comprises 1) a light-weight eye tracking headset, 2) an open source software framework for mobile eye tracking, as well as 3) a graphical user interface to playback and visualize video and gaze data. Pupil features high-resolution scene and eye cameras for monocular and binocular gaze estimation. The software and GUI are platform-independent and include state-of-the-art algorithms for real-time pupil detection and tracking, calibration, and accurate gaze estimation. Results of a performance evaluation show that Pupil can provide an average gaze estimation accuracy of 0.6 degree of visual angle (0.08 degree precision) with a processing pipeline latency of only 0.045 seconds.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } In this paper we present Pupil -- an accessible, affordable, and extensible open source platform for pervasive eye tracking and gaze-based interaction. Pupil comprises 1) a light-weight eye tracking headset, 2) an open source software framework for mobile eye tracking, as well as 3) a graphical user interface to playback and visualize video and gaze data. Pupil features high-resolution scene and eye cameras for monocular and binocular gaze estimation. The software and GUI are platform-independent and include state-of-the-art algorithms for real-time pupil detection and tracking, calibration, and accurate gaze estimation. Results of a performance evaluation show that Pupil can provide an average gaze estimation accuracy of 0.6 degree of visual angle (0.08 degree precision) with a processing pipeline latency of only 0.045 seconds. |
 | Mark Simkin; Dominique Schröder; Andreas Bulling; Mario Fritz Ubic: Bridging the Gap between Digital Cryptography and the Physical World Inproceedings Proc. of the 19th European Symposium on Research in Computer Security (ESORICS 2014), pp. 56-75, Springer International Publishing, 2014, ISBN: 978-3-319-11202-2. @inproceedings{Simkin14_ubic, title = {Ubic: Bridging the Gap between Digital Cryptography and the Physical World}, author = {Mark Simkin and Dominique Schröder and Andreas Bulling and Mario Fritz}, url = {//dx.doi.org/10.1007/978-3-319-11203-9_4 //perceptual.mpi-inf.mpg.de/files/2014/09/Simkin14_ubic1.pdf}, isbn = {978-3-319-11202-2}, year = {2014}, date = {2014-09-01}, urldate = {2014-09-18}, booktitle = {Proc. of the 19th European Symposium on Research in Computer Security (ESORICS 2014)}, volume = {8712}, pages = {56-75}, publisher = {Springer International Publishing}, abstract = {Advances in computing technology increasingly blur the boundary between the digital domain and the physical world. Although the research community has developed a large number of cryptographic primitives and has demonstrated their usability in all-digital communication, many of them have not yet made their way into the real world due to usability aspects. We aim to make another step towards a tighter integration of digital cryptography into real world interactions. We describe Ubic, a framework that allows users to bridge the gap between digital cryptography and the physical world. Ubic relies on head-mounted displays, like Google Glass, resource-friendly computer vision techniques as well as mathematically sound cryptographic primitives to provide users with better security and privacy guarantees. The framework covers key cryptographic primitives, such as secure identification, document verification using a novel secure physical document format, as well as content hiding. To make a contribution of practical value, we focused on making Ubic as simple, easily deployable, and user friendly as possible.}, key = {Usable security; head-mounted displays; ubiquitous cryptography; authentication; content verificatio}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Advances in computing technology increasingly blur the boundary between the digital domain and the physical world. Although the research community has developed a large number of cryptographic primitives and has demonstrated their usability in all-digital communication, many of them have not yet made their way into the real world due to usability aspects. We aim to make another step towards a tighter integration of digital cryptography into real world interactions. We describe Ubic, a framework that allows users to bridge the gap between digital cryptography and the physical world. Ubic relies on head-mounted displays, like Google Glass, resource-friendly computer vision techniques as well as mathematically sound cryptographic primitives to provide users with better security and privacy guarantees. The framework covers key cryptographic primitives, such as secure identification, document verification using a novel secure physical document format, as well as content hiding. To make a contribution of practical value, we focused on making Ubic as simple, easily deployable, and user friendly as possible. |
 | Yanxia Zhang; Andreas Bulling; Hans Gellersen Pupil-canthi-ratio: a calibration-free method for tracking horizontal gaze direction Inproceedings Proc. International Conference on Advanced Visual Interfaces (AVI), pp. 129-132, ACM, New York, NY, USA, 2014, ISBN: 978-1-4503-2775-6. @inproceedings{zhang14_avi, title = {Pupil-canthi-ratio: a calibration-free method for tracking horizontal gaze direction}, author = {Yanxia Zhang and Andreas Bulling and Hans Gellersen}, url = {//dx.doi.org/10.1145/2598153.2598186 //perceptual.mpi-inf.mpg.de/files/2014/09/p129-zhang1.pdf}, isbn = { 978-1-4503-2775-6}, year = {2014}, date = {2014-05-27}, booktitle = {Proc. International Conference on Advanced Visual Interfaces (AVI)}, pages = {129-132}, publisher = {ACM}, address = {New York, NY, USA}, abstract = {Eye tracking is compelling for hands-free interaction with pervasive displays. However, most existing eye tracking systems require specialised hardware and explicit calibrations of equipment and individual users, which inhibit their widespread adoption. In this work, we present a light-weight and calibration-free gaze estimation method that leverages only an off-the-shelf camera to track users' gaze horizontally. We introduce pupil-canthi-ratio (PCR), a novel measure for estimating gaze directions. By using the displacement vector between the inner eye corner and the pupil centre of an eye, PCR is calculated as the ratio of the displacement vectors from both eyes. We establish a mapping between PCR to gaze direction by Gaussian process regression, which inherently infers averted horizontal gaze directions of users. We present a study to identify the characteristics of PCR. The results show that PCR achieved an average accuracy of 3.9 degrees across different people. Finally, we show examples of real-time applications of PCR that allow users to interact with a display by moving only their eyes.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Eye tracking is compelling for hands-free interaction with pervasive displays. However, most existing eye tracking systems require specialised hardware and explicit calibrations of equipment and individual users, which inhibit their widespread adoption. In this work, we present a light-weight and calibration-free gaze estimation method that leverages only an off-the-shelf camera to track users' gaze horizontally. We introduce pupil-canthi-ratio (PCR), a novel measure for estimating gaze directions. By using the displacement vector between the inner eye corner and the pupil centre of an eye, PCR is calculated as the ratio of the displacement vectors from both eyes. We establish a mapping between PCR to gaze direction by Gaussian process regression, which inherently infers averted horizontal gaze directions of users. We present a study to identify the characteristics of PCR. The results show that PCR achieved an average accuracy of 3.9 degrees across different people. Finally, we show examples of real-time applications of PCR that allow users to interact with a display by moving only their eyes. |
 | Erroll Wood; Andreas Bulling EyeTab: Model-based gaze estimation on unmodified tablet computers Inproceedings Proc. of the 8th Symposium on Eye Tracking Research & Applications (ETRA 2014), pp. 207-210, ACM, New York, NY, USA, 2014, ISBN: 978-1-4503-2751-0. @inproceedings{wood14_etra, title = {EyeTab: Model-based gaze estimation on unmodified tablet computers}, author = { Erroll Wood and Andreas Bulling}, url = {//github.com/errollw/EyeTab/ //dx.doi.org/10.1145/2578153.2578185 //perceptual.mpi-inf.mpg.de/files/2014/10/wood14_etra.pdf}, isbn = {978-1-4503-2751-0}, year = {2014}, date = {2014-03-26}, booktitle = {Proc. of the 8th Symposium on Eye Tracking Research & Applications (ETRA 2014)}, pages = {207-210}, publisher = {ACM}, address = {New York, NY, USA}, abstract = {Despite the widespread use of mobile phones and tablets, hand-held portable devices have only recently been identified as a promising platform for gaze-aware applications. Estimating gaze on portable devices is challenging given their limited computational resources, low quality integrated front-facing RGB cameras, and small screens to which gaze is mapped. In this paper we present EyeTab, a model-based approach for binocular gaze estimation that runs entirely on an unmodified tablet. EyeTab builds on set of established image processing and computer vision algorithms and adapts them for robust and near-realtime gaze estimation. A technical prototype evaluation with eight participants in a normal indoors office setting shows that EyeTab achieves an average gaze estimation accuracy of 6.88° of visual angle at 12 frames per second.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Despite the widespread use of mobile phones and tablets, hand-held portable devices have only recently been identified as a promising platform for gaze-aware applications. Estimating gaze on portable devices is challenging given their limited computational resources, low quality integrated front-facing RGB cameras, and small screens to which gaze is mapped. In this paper we present EyeTab, a model-based approach for binocular gaze estimation that runs entirely on an unmodified tablet. EyeTab builds on set of established image processing and computer vision algorithms and adapts them for robust and near-realtime gaze estimation. A technical prototype evaluation with eight participants in a normal indoors office setting shows that EyeTab achieves an average gaze estimation accuracy of 6.88° of visual angle at 12 frames per second. |
 | Jayson Turner; Andreas Bulling; Jason Alexander; Hans Gellersen Cross-Device Gaze-Supported Point-to-Point Content Transfer Inproceedings Proc. of the 8th Symposium on Eye Tracking Research & Applications (ETRA 2014), pp. 19-26, ACM, New York, NY, USA, 2014, ISBN: 978-1-4503-2751-0. @inproceedings{turner14_etra, title = {Cross-Device Gaze-Supported Point-to-Point Content Transfer}, author = { Jayson Turner and Andreas Bulling and Jason Alexander and Hans Gellersen}, url = {//dx.doi.org/10.1145/2578153.2578155 //perceptual.mpi-inf.mpg.de/files/2014/10/Turner14_etra.pdf}, isbn = {978-1-4503-2751-0}, year = {2014}, date = {2014-03-26}, booktitle = {Proc. of the 8th Symposium on Eye Tracking Research & Applications (ETRA 2014)}, pages = {19-26}, publisher = {ACM}, address = {New York, NY, USA}, abstract = {Within a pervasive computing environment, we see content on shared displays that we wish to acquire and use in a specific way i.e., with an application on a personal device, transferring from point-to-point. The eyes as input can indicate intention to interact with a service, providing implicit pointing as a result. In this paper we investigate the use of gaze and manual input for the positioning of gaze-acquired content on personal devices. We evaluate two main techniques, (1) Gaze Positioning, transfer of content using gaze with manual input to confirm actions, (2) Manual Positioning, content is selected with gaze but final positioning is performed by manual input, involving a switch of modalities from gaze to manual input. A first user study compares these techniques applied to direct and indirect manual input configurations, a tablet with touch input and a laptop with mouse input. A second study evaluated our techniques in an application scenario involving distractor targets. Our overall results showed general acceptance and understanding of all conditions, although there were clear individual user preferences dependent on familiarity and preference toward gaze, touch, or mouse input.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Within a pervasive computing environment, we see content on shared displays that we wish to acquire and use in a specific way i.e., with an application on a personal device, transferring from point-to-point. The eyes as input can indicate intention to interact with a service, providing implicit pointing as a result. In this paper we investigate the use of gaze and manual input for the positioning of gaze-acquired content on personal devices. We evaluate two main techniques, (1) Gaze Positioning, transfer of content using gaze with manual input to confirm actions, (2) Manual Positioning, content is selected with gaze but final positioning is performed by manual input, involving a switch of modalities from gaze to manual input. A first user study compares these techniques applied to direct and indirect manual input configurations, a tablet with touch input and a laptop with mouse input. A second study evaluated our techniques in an application scenario involving distractor targets. Our overall results showed general acceptance and understanding of all conditions, although there were clear individual user preferences dependent on familiarity and preference toward gaze, touch, or mouse input. |
 | Shoya Ishimaru; Jens Weppner; Kai Kunze; Koichi Kise; Andreas Dengel; Paul Lukowicz; Andreas Bulling In the Blink of an Eye - Combining Head Motion and Eye Blink Frequency for Activity Recognition with Google Glass Inproceedings Proc. of the 5th Augmented Human International Conference (AH 2014), ACM, New York, NY, USA, 2014, ISBN: 978-1-4503-2761-9. @inproceedings{ishimaru14_ah, title = {In the Blink of an Eye - Combining Head Motion and Eye Blink Frequency for Activity Recognition with Google Glass}, author = { Shoya Ishimaru and Jens Weppner and Kai Kunze and Koichi Kise and Andreas Dengel and Paul Lukowicz and Andreas Bulling}, url = {//dx.doi.org/10.1145/2582051.2582066 //perceptual.mpi-inf.mpg.de/files/2014/10/ishimaru14_ah.pdf}, isbn = {978-1-4503-2761-9}, year = {2014}, date = {2014-03-07}, booktitle = {Proc. of the 5th Augmented Human International Conference (AH 2014)}, number = {15}, publisher = {ACM}, address = {New York, NY, USA}, abstract = {We demonstrate how information about eye blink frequency and head motion patterns derived from Google Glass sensors can be used to distinguish different types of high level activities. While it is well known that eye blink frequency is correlated with user activity, our aim is to show that (1) eye blink frequency data from an unobtrusive, commercial platform which is not a dedicated eye tracker is good enough to be useful and (2) that adding head motion patterns information significantly improves the recognition rates. The method is evaluated on a data set from an experiment containing five activity classes (reading, talking, watching TV, mathematical problem solving, and sawing) of eight participants showing 67% recognition accuracy for eye blinking only and 82% when extended with head motion patterns.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } We demonstrate how information about eye blink frequency and head motion patterns derived from Google Glass sensors can be used to distinguish different types of high level activities. While it is well known that eye blink frequency is correlated with user activity, our aim is to show that (1) eye blink frequency data from an unobtrusive, commercial platform which is not a dedicated eye tracker is good enough to be useful and (2) that adding head motion patterns information significantly improves the recognition rates. The method is evaluated on a data set from an experiment containing five activity classes (reading, talking, watching TV, mathematical problem solving, and sawing) of eight participants showing 67% recognition accuracy for eye blinking only and 82% when extended with head motion patterns. |
 | Sikandar Amin; Philipp Müller; Andreas Bulling; Mykhaylo Andriluka Test-time Adaptation for 3D Human Pose Estimation Inproceedings Proc. of the 36th German Conference on Pattern Recognition (GCPR 2014), pp. 253-26, 2014. @inproceedings{amin14_gcpr, title = {Test-time Adaptation for 3D Human Pose Estimation}, author = { Sikandar Amin and Philipp Müller and Andreas Bulling and Mykhaylo Andriluka}, url = {//perceptual.mpi-inf.mpg.de/files/2014/10/amin14_gcpr.pdf //link.springer.com/chapter/10.1007%2F978-3-319-11752-2_20}, doi = {10.1007/978-3-319-11752-2_20}, year = {2014}, date = {2014-01-01}, booktitle = {Proc. of the 36th German Conference on Pattern Recognition (GCPR 2014)}, pages = {253-26}, abstract = {In this paper we consider the task of articulated 3D human pose estimation in challenging scenes with dynamic background and multiple people. Initial progress on this task has been achieved building on discriminatively trained part-based models that deliver a set of 2D body pose candidates that are then subsequently refined by reasoning in 3D [1, 4, 5]. The performance of such methods is limited by the performance of the underlying 2D pose estimation approaches. In this paper we explore a way to boost the performance of 2D pose estimation based on the output of the 3D pose reconstruction process, thus closing the loop in the pose estimation pipeline. We build our approach around a component that is able to identify true positive pose estimation hypotheses with high confidence. We then either retrain 2D pose estimation models using such highly confident hypotheses as additional training examples, or we use similarity o these hypotheses as a cue for 2D pose estimation. We consider a number of features that can be used for assessing the confidence of the pose estimation results. The strongest feature in our comparison corresponds to the ensemble greement on the 3D pose output. We evaluate our approach on two publicly available datasets improving over state of the art in each case. }, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } In this paper we consider the task of articulated 3D human pose estimation in challenging scenes with dynamic background and multiple people. Initial progress on this task has been achieved building on discriminatively trained part-based models that deliver a set of 2D body pose candidates that are then subsequently refined by reasoning in 3D [1, 4, 5]. The performance of such methods is limited by the performance of the underlying 2D pose estimation approaches. In this paper we explore a way to boost the performance of 2D pose estimation based on the output of the 3D pose reconstruction process, thus closing the loop in the pose estimation pipeline. We build our approach around a component that is able to identify true positive pose estimation hypotheses with high confidence. We then either retrain 2D pose estimation models using such highly confident hypotheses as additional training examples, or we use similarity o these hypotheses as a cue for 2D pose estimation. We consider a number of features that can be used for assessing the confidence of the pose estimation results. The strongest feature in our comparison corresponds to the ensemble greement on the 3D pose output. We evaluate our approach on two publicly available datasets improving over state of the art in each case. |
book chapters
 | Päivi Majaranta; Andreas Bulling Eye Tracking and Eye-Based Human-Computer Interaction Book Chapter Fairclough, Stephen H; Gilleade, Kiel (Ed.): pp. 39-65, Springer, 2014, ISBN: 978-1-4471-6391-6. @inbook{majaranta14_apc, title = {Eye Tracking and Eye-Based Human-Computer Interaction}, author = {Päivi Majaranta and Andreas Bulling}, editor = {Stephen H. Fairclough and Kiel Gilleade}, url = {//dx.doi.org/10.1007/978-1-4471-6392-3_3 //perceptual.mpi-inf.mpg.de/files/2014/07/majaranta14_apc.pdf}, isbn = {978-1-4471-6391-6}, year = {2014}, date = {2014-04-01}, pages = {39-65}, publisher = {Springer}, series = {Advances in Physiological Computing}, abstract = {Eye tracking has a long history in medical and psychological research as a tool for recording and studying human visual behavior. Real-time gaze-based text entry can also be a powerful means of communication and control for people with physical disa-bilities. Following recent technological advances and the advent of affordable eye trackers, there is a growing interest in pervasive at-tention-aware systems and interfaces that have the potential to rev-olutionize mainstream human-technology interaction. In this chapter, we provide an introduction to the state-of-the art in eye tracking technology and gaze estimation. We discuss challenges involved in using a perceptual organ, the eye, as an input modality. Examples of real life applications are reviewed, together with design solutions derived from research results. We also discuss how to match the user requirements and key features of different eye tracking sys-tems to find the best system for each task and application.}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } Eye tracking has a long history in medical and psychological research as a tool for recording and studying human visual behavior. Real-time gaze-based text entry can also be a powerful means of communication and control for people with physical disa-bilities. Following recent technological advances and the advent of affordable eye trackers, there is a growing interest in pervasive at-tention-aware systems and interfaces that have the potential to rev-olutionize mainstream human-technology interaction. In this chapter, we provide an introduction to the state-of-the art in eye tracking technology and gaze estimation. We discuss challenges involved in using a perceptual organ, the eye, as an input modality. Examples of real life applications are reviewed, together with design solutions derived from research results. We also discuss how to match the user requirements and key features of different eye tracking sys-tems to find the best system for each task and application. |
