Combining Orientation Tensors for Human Action Recognition
Virgínia Fernandes Mota, Jessica I.C. Souza, Arnaldo de Albuquerque Araújo, Marcelo Bernardes Vieira · 2013
This paper presents a new tensor motion descriptor based on histogram of oriented gradients. We model the temporal evolution of gradient distribution with orientation tensors in equally sized blocks throughout the video sequence. Subsequently, these blocks are concatenated to create the final descriptor. Using a SVM classifier, even without any bag-of-feature based approach, our method achieves recognition rates greater than those found by other HOG techniques on KTH dataset and a competitive recognition rate for UCF11 and Hollywood2 datasets.