This paper presents a content-based approach for temporal segmentation of videos. Tracked objects are characterized by their 2D trajectories which are used in a meaningful way to ...
Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre L...
We propose dynamical systems trees (DSTs) as a flexible model for describing multiple processes that interact via a hierarchy of aggregating processes. DSTs extend nonlinear dynam...
Standard hidden Markov models (HMM's) have been studied extensively in the last two decades. It is well known that these models assume state conditional independence of the ob...
We present the use of layered probabilistic representations for modeling human activities, and describe how we use the representation to do sensing, learning, and inference at mul...
The work presents the first effort to automatically annotate the semantic meanings of temporal video patterns obtained through unsupervised discovery processes. This problem is in...
Lexing Xie, Lyndon S. Kennedy, Shih-Fu Chang, Ajay...