Knowledge Commons of Institute of Automation,CAS
Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification | |
Du Y(杜杨)1,2,3,4,5; Chunfeng Yuan2,3; Bing Li2,3; Lili Zhao4; Yangxi Li5; Weiming Hu2,3,5 | |
2018-09 | |
会议名称 | European Conference on Computer Vision (ECCV2018) |
会议录名称 | Procedings of European Conference on Computer Vision (ECCV2018) |
页码 | pp. 388-404. |
会议日期 | 2018-09-08---2018-09-14 |
会议地点 | Munich, Germany |
会议录编者/会议主办者 | Committee of ECCV 2018 |
摘要 | Local features at neighboring spatial positions in feature maps have high correlation since their receptive fields are often overlapped. Self-attention usually uses the weighted sum (or other functions) with internal elements of each local feature to obtain its weight score, which ignores interactions among local features. To address this, we propose an effective interaction-aware self-attention model inspired by PCA to learn attention maps. Furthermore, since different layers in a deep network capture feature maps of dfferent scales, we use these feature maps to construct a spatial pyramid and then utilize multi-scale information to obtain more accurate attention scores, which are used to weight the local features in all spatial positions of feature maps to calculate attention maps. Moreover, our spatial pyramid attention is unrestricted to the number of its input feature maps so it is easily extended to a spatiotemporal version. Finally, our model is embedded in general CNNs to form end-to-end attention networks for action classification. Experimental results show that our method achieves the state-of-the-art results on the UCF101, HMDB51 and untrimmed Charades. |
学科门类 | 工学 |
收录类别 | EI |
语种 | 英语 |
WOS记录号 | WOS:000853875300082 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23366 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
作者单位 | 1.中国科学院大学 2.中国科学院脑科学与智能技术卓越创新中心(神经科学研究所) 3.中国科学院自动化研究所 4.Meitu, Mainland China 5.国家计算机网络应急技术处理协调中心 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Du Y,Chunfeng Yuan,Bing Li,et al. Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification[C]//Committee of ECCV 2018,2018:pp. 388-404.. |
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 | ||
eccv2018.pdf(6727KB) | 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