The Perceptual User Interfaces (PUI) research group at the Max Planck Institute for Informatics, headed by Dr. Andreas Bulling, invites applications for fully funded PhD studentships on 1) Pervasive gaze estimation and attention analysis 2) Pervasive eye-based human-computer interfaces and 3) Eye-based context-awareness. For more details on the available PhD studentships please see below. Contact information: Dr. Andreas Bulling Perceptual User Interfaces Group Max Planck Institute for Informatics Email: [email protected] Web: http://www.mpi-inf.mpg.de/~bulling/ --------------------------------------------------------------------------------------- STUDENTSHIP 1 --------------------------------------------------------------------------------------- Computer vision is a powerful sensing modality and a key component in state-of-the-art eye tracking systems. However, computer vision also still represents one of its major limitations, particularly in unconstrained daily life settings in which many of the assumptions on which existing algorithms rely can typically not be satisfied, such as stable lighting conditions, stable body and head position, or special-purpose and high-quality cameras. Continuous gaze estimation throughout the day, so-called pervasive eye tracking, promises a paradigm shift in our understanding of how the eyes can be used as an input modality and source of information on user attention. The proposed PhD project will develop and study image processing and computer vision techniques for pervasive gaze estimation and attention analysis. Potential applications are in visual behaviour monitoring, human- computer interaction, context-aware computing and experimental psychology. The research will be experimental, using stationary and portable cameras and camera systems, and will involve user studies and data collection in daily life settings. In addition to experimental skills, the work will require to develop a thorough understanding of image processing, computer vision and machine learning techniques suitable for pervasive gaze estimation and attention analysis. The research directions of particular interest include but are not limited to: * Real-time image processing algorithms for pupil detection, tracking and gaze estimation in pervasive settings * Computer vision and machine learning for attention analysis on situated and hand-held portable devices * Image processing and computer vision techniques for multimodal human-computer interaction The Max Planck Institute for Informatics offers a highly collegiate and stimulating environment for doctoral research training. The successful candidate will join a young and ambitious research group that is at the forefront of this emerging research area. The candidate will be expected to contribute to the strong profile of the group by participating in the preparation and publication of research results at the level of international excellence. We invite applications from enthusiastic individuals, who are able to work independently and have an excellent first degree in Computer Science or a related field relevant to the proposed research, and very good knowledge of image processing, computer vision or machine learning for computer vision. The studentship is not restricted by nationality. Interested applicants are advised to consult previous work on pervasive eye tracking [1,2]. Applicants are also strongly encouraged to initiate contact with Dr. Andreas Bulling prior to their application. Applicants should submit their CV, a copy of school and university degree and course transcripts with grades (Abitur, Vor- and Hauptdiplom for German applicants), names and contact information of two references, a description of research interests and a short research proposal. Incomplete applications will not be considered. Applications should be emailed to [email protected] Review of applications will start on 1st March 2013. Applications are accepted until the position is filled. [1] L. Swirski, A. Bulling, N. Dodgson (2012) Robust, real-time pupil tracking in highly off-axis images, Proc. ETRA 2012: pages 173-176 http://dx.doi.org/10.1145/2168556.2168585 [2] Y. Zhang, A. Bulling, H. Gellersen (2012) Towards pervasive gaze tracking with low-level image features, Proc. ETRA 2012: pages 261-264 http://dx.doi.org/10.1145/2168556.2168611 --------------------------------------------------------------------------------------- STUDENTSHIP 2 --------------------------------------------------------------------------------------- Existing work on eye-based human-computer interaction mainly developed use of the eyes in stationary ("desktop") settings that involved single user, single device and WIMP-style interactions. Pervasive eye tracking - continuous eye tracking and analysis 24/7 - promises a paradigm shift in how the eyes are used as an input modality and points the way towards a new class of pervasive eye-based human-computer interfaces. Pervasive eye-based human-computer interfaces aim to analyse and exploit the information contained in visual behaviour in all explicit and implicit interactions that people perform with computing systems throughout the day. The proposed PhD project will develop and study interaction techniques and models for pervasive eye-based human-computer interaction. Potential applications are in multimodal and attentive user interfaces, mobile virtual reality systems, information visualisation and automotive interfaces. The research will be experimental, using stationary and portable eye tracking equipment and wearable sensor systems, and will involve controlled user studies and data collection in daily life settings. In addition to experimental skills, the work will require to develop a thorough understanding of cognitive and physical ergonomics, the design and implementation of prototype interactive systems, as well as statistical data analysis techniques suitable for evaluating and characterising human-computer interfaces. The research directions of particular interest include but are not limited to: * Interaction techniques and models for pervasive eye-based single and multi-user human-computer interaction * Real-time user interfaces that rely on multiple input modalities, such as gaze, body movements or speech * Pervasive eye-based interaction for security and privacy, information visualisation, and mobile virtual reality The Max Planck Institute for Informatics offers a highly collegiate and stimulating environment for doctoral research training. The successful candidate will join a young and ambitious research group that is at the forefront of this emerging research area. The candidate will be expected to contribute to the strong profile of the group by participating in the preparation and publication of research results at the level of international excellence. We invite applications from enthusiastic individuals, who are able to work independently and have an excellent first degree in Computer Science or a related field relevant to the proposed research, and very good knowledge of human-computer interaction or media informatics. The studentship is not restricted by nationality. Interested applicants are advised to consult previous work on pervasive eye-based human-computer interaction [1,2,3]. Applicants are also strongly encouraged to initiate contact with Dr. Andreas Bulling prior to their application. Applicants should submit their CV, a copy of school and university degree and course transcripts with grades (Abitur, Vor- and Hauptdiplom for German applicants), names and contact information of two references, a description of research interests and a short research proposal. Incomplete applications will not be considered. Applications should be emailed to [email protected] Review of applications will start on 1st March 2013. Applications are accepted until the position is filled. [1] Y. Zhang, A. Bulling, H. Gellersen (2013) SideWays: A Gaze Interface for Spontaneous Interaction with Situated Displays, Proc. CHI 2013, to appear https://www.andreas-bulling.de/fileadmin/docs/zhang13_chi.pdf [2] J. Turner, A. Bulling, H. Gellersen (2012) Extending the Visual Field of a Head-Mounted Eye Tracker for Pervasive Eye-Based Interaction, Proc. ETRA 2012: pages 269-272 http://dx.doi.org/10.1145/2168556.2168613 [3] A. Bulling, H. Gellersen (2010) Toward Mobile Eye-Based Human-Computer Interaction, IEEE Pervasive Computing, 9(4):8-12 http://dx.doi.org/10.1109/MPRV.2010.86 --------------------------------------------------------------------------------------- STUDENTSHIP 3 --------------------------------------------------------------------------------------- Context-awareness has emerged as a key area of research in ubiquitous computing and human-computer interaction (HCI). A promising new source of context information is in the movements of the eyes. The movement patterns our eyes perform as we carry out different activities reveal a lot about the activities themselves and the underlying cognitive processes. In a similar manner, location or a particular environment may influence our eye movements. Because we use our eyes in almost everything that we do, eye movement analysis has the potential to provide useful information for a variety of context recognition problems. The proposed PhD project will develop and study pattern recognition methods and machine learning techniques for context inference based on eye movement analysis. Potential applications are in activity and health monitoring, location-awareness, assisted living, and cognition-aware user interfaces. The research will be experimental, using portable eye tracking equipment and wearable sensor systems, and will involve user studies and data collection in daily life settings. In addition to experimental skills, the work will require to develop a thorough understanding of pattern recognition, machine learning and statistical signal processing techniques suitable for inferring various aspects of context from eye movements. The research directions of particular interest include but are not limited to: * Pattern recognition methods and eye movement features for modelling of visual behaviour * Machine learning techniques for context inference from eye movements * Context inference from simultaneous monitoring of eye and body movements in daily life settings The Max Planck Institute for Informatics offers a highly collegiate and stimulating environment for doctoral research training. The successful candidate will join a young and ambitious research group that is at the forefront of this emerging research area. The candidate will be expected to contribute to the strong profile of the group by participating in the preparation and publication of research results at the level of international excellence. We invite applications from enthusiastic individuals, who are able to work independently and have an excellent first degree in Computer Science or a related field relevant to the proposed research, and very good knowledge of machine learning, pattern recognition, or statistical signal processing. The studentship is not restricted by nationality. Interested applicants are advised to consult previous work on eye-based recognition of activities and cognitive processes [1,2,3]. Applicants are also strongly encouraged to initiate contact with Dr. Andreas Bulling prior to their application. Applicants should submit their CV, a copy of school and university degree and course transcripts with grades (Abitur, Vor- and Hauptdiplom for German applicants), names and contact information of two references, a description of research interests and a short research proposal. Incomplete applications will not be considered. Applications should be emailed to [email protected] Review of applications will start on 1st March 2013. Applications are accepted until the position is filled. [1] A. Bulling, J. Ward, H. Gellersen (2012) Multimodal Recognition of Reading Activity in Transit Using Body-Worn Sensors, ACM Transactions on Applied Perception, 9(1):2:1-2:21 http://dx.doi.org/10.1145/2134203.2134205 [2] A. Bulling, J. Ward, H. Gellersen, G. Troster (2011) Eye Movement Analysis for Activity Recognition Using Electrooculography, IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(4):741-753 http://dx.doi.org/10.1109/TPAMI.2010.86 [3] A. Bulling and D. Roggen (2011) Recognition of Visual Memory Recall Processes Using Eye Movement Analysis, Proc. UbiComp 2011: pages 455-464 http://dx.doi.org/10.1145/2030112.2030172 --

※ 發信站: 批踢踢實業坊(ptt.cc) ◆ From: 147.46.241.183