Attention-Aware Sampling via Deep Reinforcement Learning for Action Recognition | |
Dong, Wenkai1,3; Zhang, Zhaoxiang1,2,3; Tan, Tieniu1,2,3 | |
2019 | |
会议名称 | AAAI Conference on Artificial Intelligence |
会议日期 | January 27 – February 1, 2019 |
会议地点 | Hilton Hawaiian Village, Honolulu, Hawaii, USA |
出版者 | AAAI |
摘要 | Deep learning based methods have achieved remarkable progress in action recognition. Existing works mainly focus on designing novel deep architectures to achieve video representations learning for action recognition. Most methods treat sampled frames equally and average all the frame-level predictions at the testing stage. However, within a video, discriminative actions may occur sparsely in a few frames and most other frames are irrelevant to the ground truth and may even lead to a wrong prediction. As a result, we think that the strategy of selecting relevant frames would be a further important key to enhance the existing deep learning based action recognition. In this paper, we propose an attentionaware sampling method for action recognition, which aims to discard the irrelevant and misleading frames and preserve the most discriminative frames. We formulate the process of mining key frames from videos as a Markov decision process and train the attention agent through deep reinforcement learning without extra labels. The agent takes features and predictions from the baseline model as input and generates importance scores for all frames. Moreover, our approach is extensible, which can be applied to different existing deep learning based action recognition models. We achieve very competitive action recognition performance on two widely used action recognition datasets. |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48633 |
专题 | 智能感知与计算研究中心 |
通讯作者 | Zhang, Zhaoxiang |
作者单位 | 1.Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR) 2.Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), Institute of Automation, Chinese Academy of Sciences (CASIA) 3.University of Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室; 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Dong, Wenkai,Zhang, Zhaoxiang,Tan, Tieniu. Attention-Aware Sampling via Deep Reinforcement Learning for Action Recognition[C]:AAAI,2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
4836-Article Text-79(506KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论