International Journal of Computer Vision
A 3-dimensional sift descriptor and its application to action recognition
Proceedings of the 15th international conference on Multimedia
Robust Object Detection with Interleaved Categorization and Segmentation
International Journal of Computer Vision
MM '09 Proceedings of the 17th ACM international conference on Multimedia
An overview of contest on semantic description of human activities (SDHA) 2010
ICPR'10 Proceedings of the 20th International conference on Recognizing patterns in signals, speech, images, and videos
Real-time human action search using random forest based hough voting
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Recognizing interaction between human performers using 'key pose doublet'
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Fast Action Detection via Discriminative Random Forest Voting and Top-K Subvolume Search
IEEE Transactions on Multimedia
Human activity prediction: Early recognition of ongoing activities from streaming videos
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Propagative hough voting for human activity recognition
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I
Hi-index | 0.00 |
Early recognition and prediction of human activities are of great importance in video surveillance, e.g., by recognizing a criminal activity at its beginning stage, it is possible to avoid unfortunate outcomes. We address early activity recognition by developing a Spatial-Temporal Implicit Shape Model (STISM), which characterizes the space-time structure of the sparse local features extracted from a video. The early recognition of human activities is accomplished by pattern matching through STISM. To enable efficient and robust matching, we propose a new random forest structure, called multi-class balanced random forest, which makes a good trade-off between the balance of the trees and the discriminative abilities. The prediction is done simultaneously for multiple classes, which saves both the memory and computational cost. The experiments show that our algorithm significantly outperforms the state of the arts for the human activity prediction problem.