WHEN SKELETON MEETS APPEARANCE: ADAPTIVE APPEARANCE INFORMATION ENHANCEMENT FOR SKELETON BASED ACTION RECOGNITION

CASIA OpenIR > 紫东太初大模型研究中心

	WHEN SKELETON MEETS APPEARANCE: ADAPTIVE APPEARANCE INFORMATION ENHANCEMENT FOR SKELETON BASED ACTION RECOGNITION
	Wang Suqin 1,2; Zhou Lu1,2 ; Chen Yingying1,2,3 ; Jiangtao Huo 4; Wang Jinqiao1,2
	2022
会议名称	International Conference on Multimedia and Expo
会议日期	July 18-22, 2022
会议地点	中国台北
摘要	Skeleton-based action recognition methods which utilize graph convolution networks (GCNs) have achieved remark able success in recent years. However, action recognizer can be easily confused by the ambiguity caused by different ac tions with similar skeleton sequences when only skeleton data is trained. Introducing appearance information can effectively eliminate the ambiguity. Based on this, we introduce a two stream network for action recognition. One trained on RGB images extracts appearance information. The other trained on skeleton data models motion information and adaptively captures appearance information of action areas at action related intervals via a specially tailored attention mechanism. Our architecture is trained and evaluated on two large-scale datasets: NTU RGB+D and NTU RGB+D 120, and a small scale human-object interaction dataset Northwestern-UCLA. Experiment results verify the effectiveness of our method and the performance of our method exceeds the state-of-the-art with a significant margin.
收录类别	EI
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	视觉信息处理
是否有论文关联数据集需要存交	否
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/57151
专题	紫东太初大模型研究中心
作者单位	1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Development Research Institute of Guangzhou Smart City 4.Army Medical University, NCO School of PLA
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Wang Suqin,Zhou Lu,Chen Yingying,et al. WHEN SKELETON MEETS APPEARANCE: ADAPTIVE APPEARANCE INFORMATION ENHANCEMENT FOR SKELETON BASED ACTION RECOGNITION[C],2022.

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
When_Skeleton_Meets_（635KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载