Knowledge Commons of Institute of Automation,CAS
Spatial-Temporal Exclusive Capsule Network for Open Set Action Recognition | |
Feng, Yangbo1; Gao, Junyu2,3; Yang, Shicai4; Xu, Changsheng2,3,5 | |
发表期刊 | IEEE Transactions on Multimedia |
2023 | |
卷号 | 0期号:0页码:1-16 |
摘要 | Open set action recognition (OSAR) is a rising research domain that simultaneously identifies all videos from known classes and rejects videos from unknown classes. Existing methods rarely consider the open set data distribution and the spatial-temporal relations of video subsequence. Recently proposed Capsule Network (CapsNet) has shown robust performance in many fields, especially image recognition. However, the current CapsNet has not been directly applied to the OSAR task since it cannot explicitly consider the data distribution of known and unknown classes along with the spatial-temporal relations for videos. This paper proposes the Spatial-Temporal Exclusive Capsule Network (STE-CapsNet) to solve the problems in the OSAR task. The STE-CapsNet designs the temporal-spatial routing mechanism to jointly capture the spatial-temporal information of the videos. Furthermore, the exclusive capsules are learned with dot product routing mechanism to limit the data distribution of closed set and open set and reduce the open set risk for OSAR. Extensive experimental results demonstrate that our proposed approach performs favorably compared with state-of-the-art methods on three standard datasets, which verifies its effectiveness and generalization ability. |
其他摘要 |
|
WOS记录号 | WOS:001133324200028 |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 可解释人工智能 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51519 |
专题 | 多模态人工智能系统全国重点实验室 |
作者单位 | 1.Tianjin University of Technology 2.State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences 3.School of Artificial Intelligence, University of Chinese Academy of Sciences 4.Hikvision Research Institute 5.Peng Cheng Laboratory |
推荐引用方式 GB/T 7714 | Feng, Yangbo,Gao, Junyu,Yang, Shicai,et al. Spatial-Temporal Exclusive Capsule Network for Open Set Action Recognition[J]. IEEE Transactions on Multimedia,2023,0(0):1-16. |
APA | Feng, Yangbo,Gao, Junyu,Yang, Shicai,&Xu, Changsheng.(2023).Spatial-Temporal Exclusive Capsule Network for Open Set Action Recognition.IEEE Transactions on Multimedia,0(0),1-16. |
MLA | Feng, Yangbo,et al."Spatial-Temporal Exclusive Capsule Network for Open Set Action Recognition".IEEE Transactions on Multimedia 0.0(2023):1-16. |
条目包含的文件 | 条目无相关文件。 |
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