K
Keng Teck Ma
Researcher at Agency for Science, Technology and Research
Publications - 31
Citations - 684
Keng Teck Ma is an academic researcher from Agency for Science, Technology and Research. The author has contributed to research in topics: Personal computer & Eye tracking. The author has an hindex of 8, co-authored 31 publications receiving 594 citations. Previous affiliations of Keng Teck Ma include Institute for Infocomm Research Singapore & National University of Singapore.
Papers
More filters
Proceedings ArticleDOI
Trajectory analysis and semantic region modeling using a nonparametric Bayesian model
TL;DR: In this article, a dual hierarchical Dirichlet process (Dual-HDP) is proposed for trajectory analysis and semantic region modeling in surveillance settings, in an unsupervised way.
Journal ArticleDOI
Trajectory Analysis and Semantic Region Modeling Using Nonparametric Hierarchical Bayesian Models
TL;DR: The Dual Hierarchical Dirichlet Processes model is extended to a Dynamic Dual-HDP model which allows dynamic update of activity models and online detection of normal/abnormal activities.
Proceedings ArticleDOI
Deep Future Gaze: Gaze Anticipation on Egocentric Videos Using Adversarial Networks
TL;DR: A new generative adversarial neural network based model, Deep Future Gaze (DFG), which generates multiple future frames conditioned on the single current frame and anticipates corresponding future gazes in next few seconds and achieves better performance of gaze prediction on current frames than state-of-the-art methods.
Journal ArticleDOI
Finding any Waldo with zero-shot invariant and efficient visual search
TL;DR: It is shown for the first time that humans can efficiently and invariantly search for natural objects in complex scenes and a biologically-inspired zero-shot model that captures human eye movements during search is introduced.
Journal ArticleDOI
Anticipating Where People will Look Using Adversarial Networks
TL;DR: A new problem of gaze anticipation on future frames which extends the conventional gaze prediction problem to go beyond current frames is introduced and a new generative adversarial network based model, Deep Future Gaze (DFG), encompassing two pathways is proposed.