Training products of experts by minimizing contrastive divergence
Neural Computation
Recognizing Human Actions: A Local SVM Approach
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
A fast learning algorithm for deep belief nets
Neural Computation
A survey of advances in vision-based human motion capture and analysis
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Combining Densely Sampled Form and Motion for Human Action Recognition
Proceedings of the 30th DAGM symposium on Pattern Recognition
| Hi-index | 0.00 |
This paper presents an evaluation of two multilevel architectures in the human action recognition (HAR) task. By combining low level features with multi-layer learning architectures, we infer discriminative semantic features that highly improve the classification performance. This approach eliminates the difficult process of selecting good mid-level feature descriptors, changing the feature selection and extraction process by a learning stage. The data probability distribution is modeled by a multi-layer graphical model. In this way, this approach is different to the standard ones. Experiments on KTH and Weizmann video sequence databases are carried out in order to evaluate the performance of the proposal. The results show that the new learnt features offer a classification performance comparable to the state-of-the-art on these databases.