Better deep visual attention with reinforcement learning in action recognition
暂无分享,去创建一个
Gang Wang | Wenmin Wang | Yaohua Bu | Jingzhuo Wang | G. Wang | Yaohua Bu | J. Wang | Wenmin Wang
[1] Dumitru Erhan,et al. Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[2] Ruslan Salakhutdinov,et al. Action Recognition using Visual Attention , 2015, NIPS 2015.
[3] Christopher D. Manning,et al. Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.
[4] Andrew Zisserman,et al. Two-Stream Convolutional Networks for Action Recognition in Videos , 2014, NIPS.
[5] Xiaoou Tang,et al. Action Recognition and Detection by Combining Motion and Appearance Features , 2014 .
[6] Elsayed E. Hemayed,et al. Human action recognition using trajectory-based representation , 2015 .
[7] Alex Graves,et al. Recurrent Models of Visual Attention , 2014, NIPS.
[8] Baoxin Li,et al. Recognizing unseen actions in a domain-adapted embedding space , 2016, 2016 IEEE International Conference on Image Processing (ICIP).
[9] Li Fei-Fei,et al. End-to-End Learning of Action Detection from Frame Glimpses in Videos , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[10] Limin Wang,et al. Action recognition with trajectory-pooled deep-convolutional descriptors , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[11] Alex Graves,et al. DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.
[12] Yu Qiao,et al. Action Recognition with Stacked Fisher Vectors , 2014, ECCV.
[13] Alexander J. Smola,et al. Stacked Attention Networks for Image Question Answering , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[14] Yoshua Bengio,et al. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.
[15] Matthew J. Hausknecht,et al. Beyond short snippets: Deep networks for video classification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).