1. K. Soomro, A.R. Zamir, M. Shah, Ucf101: A dataset of 101 human actions classes from videos in the wild, arXiv preprint arXiv:1212.0402.
2. Imagenet classification with deep convolutional neural networks;Krizhevsky;Adv. Neural Inform. Process. Syst.,2012
3. Deep residual learning for image recognition;He;IEEE Conference on Computer Vision and Pattern Recognition,2016
4. Fast r-cnn;Girshick;IEEE International Conference on Computer Vision,2015
5. Faster r-cnn: Towards real-time object detection with region proposal networks;Ren;IEEE Trans. Pattern Anal. Mach. Intell.,2017