Fast parallel and serial approximate string matching
Journal of Algorithms
Text algorithms
An introduction to support Vector Machines: and other kernel-based learning methods
An introduction to support Vector Machines: and other kernel-based learning methods
The Journal of Machine Learning Research
Optimal Cluster Preserving Embedding of Nonmetric Proximity Data
IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognizing Human Actions: A Local SVM Approach
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words
International Journal of Computer Vision
The hidden permutation model and location-based activity recognition
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 3
Policy recognition in the abstract hidden Markov model
Journal of Artificial Intelligence Research
Location-based activity recognition using relational Markov networks
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Sequence-kernel based sparse representation for amateur video summarization
J-MRE '11 Proceedings of the 2011 joint ACM workshop on Modeling and representing events
| Hi-index | 0.00 |
Automatic recognition of human activities is among the key capabilities of many intelligent systems with vision/perception. Most existing approaches to this problem require sophisticated feature extraction before classification can be performed. This paper presents a novel approach for human action recognition using only simple low-level visual features: motion captured from direct frame differencing. A codebook of key poses is first created from the training data through unsupervised clustering. Videos of actions are then coded as sequences of super-frames, defined as the key poses augmented with discriminative attributes. A weighted-sequence distance is proposed for comparing two super-frame sequences, which is further wrapped as a kernel embedded in a SVM classifier for the final classification. Compared with conventional methods, our approach provides a flexible non-parametric sequential structure with a corresponding distance measure for human action representation and classification without requiring complex feature extraction. The effectiveness of our approach is demonstrated with the widely-used KTH human activity dataset, for which the proposed method outperforms the existing state-of-the-art.