Title | ||
---|---|---|
Bridging the past, present and future: Modeling scene activities from event relationships and global rules |
Abstract | ||
---|---|---|
This paper addresses the discovery of activities and learns the underlying processes that govern their occurrences over time in complex surveillance scenes. To this end, we propose a novel topic model that accounts for the two main factors that affect these occurrences: (1) the existence of global scene states that regulate which of the activities can spontaneously occur; (2) local rules that link past activity occurrences to current ones with temporal lags. These complementary factors are mixed in the probabilistic generative process, thanks to the use of a binary random variable that selects for each activity occurrence which one of the above two factors is applicable. All model parameters are efficiently inferred using a collapsed Gibbs sampling inference scheme. Experiments on various datasets from the literature show that the model is able to capture temporal processes at multiple scales: the scene-level first order Markovian process, and causal relationships amongst activities that can be used to predict which activity can happen after another one, and after what delay, thus providing a rich interpretation of the scene's dynamical content. |
Year | Venue | Keywords |
---|---|---|
2012 | CVPR | past activity occurrence,scene activity,activity occurrence,global scene state,temporal process,global rule,novel topic model,model parameter,temporal lag,complex surveillance scene,order Markovian process,event relationship,probabilistic generative process |
DocType | Citations | PageRank |
Conference | 1 | 0.36 |
References | Authors | |
0 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Remi Emonet | 1 | 103 | 8.49 |