Sciweavers

417 search results - page 42 / 84
» To learn representativeness of video frames
Sort
View
ICPR
2008
IEEE
16 years 1 months ago
Learning motion patterns in crowded scenes using motion flow field
Learning typical motion patterns or activities from videos of crowded scenes is an important visual surveillance problem. To detect typical motion patterns in crowded scenarios, w...
Min Hu, Mubarak Shah, Saad Ali
AVSS
2007
IEEE
15 years 6 months ago
Vehicular traffic density estimation via statistical methods with automated state learning
This paper proposes a novel approach of combining an unsupervised clustering scheme called AutoClass with Hidden Markov Models (HMMs) to determine the traffic density state in a R...
Evan Tan, Jing Chen
ECAI
2008
Springer
15 years 1 months ago
Learning Functional Object-Categories from a Relational Spatio-Temporal Representation
Abstract. We propose a framework that learns functional objectes from spatio-temporal data sets such as those abstracted from video. The data is represented as one activity graph t...
Muralikrishna Sridhar, Anthony G. Cohn, David C. H...
ICPR
2008
IEEE
15 years 6 months ago
Toward an interactive device for quick news story browsing
In this paper, we present a new design for an Interactive Information service based on on-line recognition of the handwriting and quick news stories browsing. A person communicate...
Monji Kherallah, Hichem Karray, Mehdi Ellouze, Ade...
CVPR
2007
IEEE
15 years 6 months ago
Visual Event Recognition in News Video using Kernel Methods with Multi-Level Temporal Alignment
In this work, we systematically study the problem of visual event recognition in unconstrained news video sequences. We adopt the discriminative kernel-based method for which vide...
Dong Xu, Shih-Fu Chang