A Video Tensor Self-descriptor Based on Block Matching

In this paper, we propose a new motion descriptor which uses only block matching vectors. This is a different and simple approach considering that most works on the field are based on the gradient of image intensities. The block matching method returns displacements vectors as a motion information. Our method computes this information to obtain orientation tensors and to generate the final descriptor. It is considered a self-descriptor, since it depends only on the input video. The global tensor descriptor is evaluated by a classification of KTH, UCF11 and Hollywood2 video datasets with a non-linear SVM classifier. Our results indicate that the method runs fast and has fairly competitive results compared to similar approaches. It is suitable when the time response is a major application issue. It also generates compact descriptors which are desirable to describe large datasets.