Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Recognizing Human Actions: A Local SVM Approach
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Local velocity-adapted motion events for spatio-temporal recognition
Computer Vision and Image Understanding
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Action recognition by dense trajectories
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Motion recognition using local auto-correlation of space-time gradients
Pattern Recognition Letters
A Tensor Based on Optical Flow for Global Description of Motion in Videos
SIBGRAPI '12 Proceedings of the 2012 25th SIBGRAPI Conference on Graphics, Patterns and Images
A local descriptor based on Laplacian pyramid coding for action recognition
Pattern Recognition Letters
| Hi-index | 0.10 |
This paper presents a new tensor motion descriptor only using optical flow and HOG3D information: no interest points are extracted and it is not based on a visual dictionary. We propose a new aggregation technique based on tensors. This is a double aggregation of tensor descriptors. The first one represents motion by using polynomial coefficients which approximates the optical flow. The other represents the accumulated data of all histograms of gradients of the video. The descriptor is evaluated by a classification of KTH, UCF11 and Hollywood2 datasets, using a SVM classifier. Our method reaches 93.2% of recognition rate with KTH, comparable to the best local approaches. For the UCF11 and Hollywood2 datasets, our recognition achieves fairly competitive results compared to local and learning based approaches.