Abstract:
We present an unsupervised technique for detecting unusual activity in a large video set using many simple features. No complex activity models and no supervised feature selections are used. We divide the video into equal length segments and classify the extracted features into prototypes, from which a prototype–segment co-occurrence matrix is computed. Motivated by a similar problem in documentkeyword analysis, we seek a correspondence relationship between prototypes and video segments which satisfies the transitive closure constraint. We show that an important sub-family of correspondence functions can be reduced to co-embedding prototypes and segments to N-D Euclidean space. We prove that an efficient, globally optimal algorithm exists for the co-embedding problem. Experiments on various real-life videos have validated our approach. 1.
Citations
|
1463
|
Indexing by Latent Semantic Analysis
– Deerwester, Dumais, et al.
- 1990
|
|
965
|
Normalized cuts and image segmentation
– Shi, Malik
- 2000
|
|
720
|
Pfinder: Realtime tracking of the human body
– Wren, Azarbayejani, et al.
- 1997
|
|
218
|
Learning patterns of activity using real-time tracking
– Stauffer, Grimson
- 2000
|
|
198
|
Coupled hidden Markov models for complex action recognition
– Brand, Oliver, et al.
- 1997
|
|
119
|
The representation and recognition of action using temporal templates
– Davis, Bobick
- 1997
|
|
118
|
Co-Clustering Documents and Words Using Bipartite Spectral Graph Partitioning
– Dhillon
- 2001
|
|
109
|
Learning the Distribution of Object Trajectories for Event Recognition
– Johnson, Hogg
- 1996
|
|
84
|
Recognizing Action at a Distance
– Efros, Berg, et al.
- 2003
|
|
61
|
III, “Exploiting Human Actions and Object Context for Recognition Tasks
– Moore, Essa, et al.
- 1999
|
|
37
|
Event Detection and Analysis from Video Streams
– Medioni, Cohen, et al.
- 2001
|
|
27
|
ªW4: Who, When, Where, What: A Real Time System for Detecting and Tracking
– Haritaoglu, Harwood, et al.
- 1998
|
|
25
|
Spectral biclustering of microarray data: coclustering genes and conditions
– Kluger, Basri, et al.
- 2003
|
|
25
|
Event-based video analysis
– Zelnik-Manor, Irani
- 2001
|
|
20
|
A probabilistic framework for semantic indexing and retrieval in video
– Naphade, Huang
- 2000
|
