高教社计算机视觉理论与实践讲义9-视频——运动的图像.pdf

Lec9 Action Recognition ·AIPKU · 人工智能引论实践课计算机视觉小班 主讲人：刘家瑛 ·AIPKU · 部分讲义来源与致谢 1. Yong Du, Wei Wang, Liang Wang. Hierarchical recurrent neural network for skeleton based action recognition. CVPR 2015. 2. Wentao Zhu, Cuiling Lan, Junliang Xing, Wenjun Zeng, Yanghao Li, Li Shen, Xiaohui Xie. Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. AAAI 2016. 3. Jun Liu, Gang Wang, Ping Hu, Ling-Yu Duan, Alex C Kot. Global context-aware attention LSTM networks for 3D action recognition. CVPR 2017. 4. Pichao Wang, Zhaoyang Li, Yonghong Hou, Wanqing Li. Action recognition based on joint trajectory maps using convolutional neural networks. ACM MM 2016. 5. Qiuhong Ke, Mohammed Bennamoun, Senjian An, Ferdous Sohel, Farid Boussaid. A new representation of skeleton sequences for 3d action recognition. CVPR 2017. 6. Karen Simonyan, Andrew Zisserman. Two-stream convolutional networks for action recognition in videos. NIPS 2014. 7. Jeffrey Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, Trevor Darrell. Long-Term recurrent convolutional networks for visual recognition and description. CVPR 2015. 2 Background 刘家瑛 Video in Big Data Era ◼ Videos in Internet ◼ Over a billion users on YouTube ◼ A billion hours of videos each day ◼ Surveillance Videos ◼ 176 million in China in 2017 ◼ Expected 626 million by 2020 3 Background 刘家瑛 Video in Big Data Era ◼ Videos in Internet ◼ Over a billion users on YouTube ◼ A billion hours of videos each day ◼ Surveillance Videos ◼ 176 million in China in 2017