1. Quo vadis, action recognition? A new model and the kinetics dataset;Carreira,2017
2. Modeling 4d human-object interactions for joint event segmentation, recognition, and object localization;Wei;IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),2017
3. K. Simonyan, A. Zisserman, Two-stream convolutional networks for action recognition in videos, in: Advances in neural information processing systems, 2014, pp. 568–576.
4. Learning composite latent structures for 3d human action representation and recognition;Wei;IEEE Transactions on Multimedia,2019
5. Going deeper with convolutions;Szegedy,2015