DMCA
Probabilistic latent sequential motifs: Discovering temporal activity patterns in video scenes (2010)
| Venue: | In British Machine Vision Conference (BMVC |
| Citations: | 17 - 8 self |
BibTeX
@INPROCEEDINGS{Varadarajan10probabilisticlatent,
author = {Jagannadan Varadarajan and Rémi Emonet and Jean-marc Odobez and École Polytechnique Fédéral De},
title = {Probabilistic latent sequential motifs: Discovering temporal activity patterns in video scenes},
booktitle = {In British Machine Vision Conference (BMVC},
year = {2010}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper introduces a novel probabilistic activity modeling approach that mines recurrent sequential patterns from documents given as word-time occurrences. In this model, documents are represented as a mixture of sequential activity motifs (or topics) and their starting occurrences. The novelties are threefold. First, unlike previous ap-proaches where topics only modeled the co-occurrence of words at a given time instant, our topics model the co-occurrence and temporal order in which the words occur within a temporal window. Second, our model accounts for the important case where activities occur concurrently in the document. And third, our method explicitly models with latent variables the starting time of the activities within the documents, enabling to implicitly align the occurrences of the same pattern during the joint inference of the temporal topics and their starting times. The model and its robustness to the presence of noise have been validated on synthetic data. Its effectiveness is also illustrated in video activity analysis from low-level motion features, where the discovered topics capture frequent patterns that implicitly represent typical trajectories of scene objects. 1
Keyphrases
temporal activity pattern probabilistic latent sequential motif video scene starting time discovered topic capture frequent pattern scene object model account joint inference temporal order important case starting occurrence time instant typical trajectory word-time occurrence novel probabilistic activity sequential activity motif temporal topic previous ap-proaches synthetic data latent variable recurrent sequential pattern video activity analysis temporal window low-level motion feature
