000192688 001__ 192688
000192688 005__ 20190125163142.0
000192688 037__ $$aCONF
000192688 245__ $$aBridging the Past, Present and Future: Modeling Scene Activities From Event Relationships and Global Rules
000192688 269__ $$a2012
000192688 260__ $$c2012
000192688 336__ $$aConference Papers
000192688 520__ $$aThis 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.
000192688 700__ $$0243361$$aVaradarajan, Jagannadan$$g179684
000192688 700__ $$aEmonet, Remi
000192688 700__ $$0243995$$aOdobez, Jean-Marc$$g161663
000192688 7112_ $$aIEEE Conference on Computer Vision and Pattern Recognition, 2012, Providence, Rhode Island, USA
000192688 909C0 $$0252189$$pLIDIAP$$xU10381
000192688 909CO $$ooai:infoscience.tind.io:192688$$pconf$$pSTI
000192688 937__ $$aEPFL-CONF-192688
000192688 970__ $$aVaradarajan_CVPR_2012/LIDIAP
000192688 973__ $$aEPFL
000192688 980__ $$aCONF