Sciweavers

417 search results - page 57 / 84
» To learn representativeness of video frames
Sort
View
CVPR
2009
IEEE
16 years 7 months ago
Observe Locally, Infer Globally: a Space-Time MRF for Detecting Abnormal Activities with Incremental Updates
We propose a space-time Markov Random Field (MRF) model to detect abnormal activities in video. The nodes in the MRF graph correspond to a grid of local regions in the video fra...
Jaechul Kim (University of Texas at Austin), Krist...
CAIP
2007
Springer
117views Image Analysis» more  CAIP 2007»
15 years 6 months ago
Eigenmotion-Based Detection of Intestinal Contractions
Abstract. Intestinal contractions are one of the main features for analyzing intestinal motility and detecting different gastrointestinal pathologies. In this paper we propose Eig...
Laura Igual, Santi Seguí, Jordi Vitri&agrav...
NIPS
2008
15 years 1 months ago
Optimization on a Budget: A Reinforcement Learning Approach
Many popular optimization algorithms, like the Levenberg-Marquardt algorithm (LMA), use heuristic-based "controllers" that modulate the behavior of the optimizer during ...
Paul Ruvolo, Ian R. Fasel, Javier R. Movellan
ECCV
2002
Springer
16 years 1 months ago
Learning to Parse Pictures of People
The detection of people is one of the foremost problems for indexing, browsing and retrieval of video. The main difficulty is the large appearance variations caused by action, clot...
Rémi Ronfard, Cordelia Schmid, Bill Triggs
CVPR
2010
IEEE
15 years 8 months ago
Clustering Dynamic Textures with the Hierarchical EM Algorithm
The dynamic texture (DT) is a probabilistic generative model, defined over space and time, that represents a video as the output of a linear dynamical system (LDS). The DT model ...
Antoni Chan, Emanuele Coviello, Gert Lanckriet