In this paper, we proposed a new human action feature descriptor which is called spatial-temporal histograms of gradients (SPHOG). SPHOG is based on the spatial ...
By doing this, the encoding schema for bag-of-feature (BOF) representation is more effective. We validated our proposed algorithm for human action recognition ...
A new spatial-temporal histograms of gradients descriptor and HOD ...
www.semanticscholar.org › paper
The evaluation experiment results indicate that the proposed descriptor and encoding method can improve the efficiency of human action recognition and the ...
We validated our proposed algorithm for human action recognition on three public available datasets KTH, UCF Sports and HMDB51. The evaluation experiment ...
Aug 20, 2018 · , Spatio-temporal VLAD encoding for human action recognition in videos, Int. Conf. Multimedia Modeling (Springer, Cham, 2017), pp. 365–378 ...
In this paper, we proposed a new human action feature descriptor which is called spatial-temporal histograms of gradients (SPHOG). SPHOG is based on the ...
It is challenging because of the complex background, illumination variations, and similar body motion in intraclass actions. ... ... One of our earlier paper [5] ...
A new spatial-temporal histograms of gradients descriptor and HOD-VLAD encoding for human action recognition · Human action recognition based on spatio-temporal ...
Jul 5, 2019 · A new histogram of oriented gradients local descriptor extraction method based on the spatio-temporal three-dimensional scattering transform ...
A new spatial-temporal histograms of gradients descriptor and HOD-VLAD encoding for human action recognition. Bo Lin ... Bin Fang. International Journal of ...