3D Single-Person Concurrent Activity Detection Using Stacked Relation Network
Yi Wei, Wenbo Li, Yanbo Fan, Linghan Xu, Ming-Ching Chang, Siwei Lyu
Abstract
We aim to detect real-world concurrent activities performed by a single person from a streaming 3D skeleton sequence. Different from most existing works that deal with concurrent activities performed by multiple persons that are seldom correlated, we focus on concurrent activities that are spatio-temporally or causally correlated and performed by a single person. For the sake of generalization, we propose an approach based on a decompositional design to learn a dedicated feature representation for each activity class. To address the scalability issue, we further extend the class-level decompositional design to the postural-primitive level, such that each class-wise representation does not need to be extracted by independent backbones, but through a dedicated weighted aggregation of a shared pool of postural primitives. There are multiple interdependent instances deriving from each decomposition. Thus, we propose Stacked Relation Networks (SRN), with a specialized relation network for each decomposition, so as to enhance the expressiveness of instance-wise representations via the inter-instance relationship modeling. SRN achieves state-of-the-art performance on a public dataset and a newly collected dataset. The relation weights within SRN are interpretable among the activity contexts. The new dataset and code are available at https://github.com/weiyi1991/UA_Concurrent/
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Related papers
- SkeleTR: Towards Skeleton-based Action Recognition in the WildHaodong Duan, Mingze Xu, Bing Shuai, Davide Modolo et al.ICCV 2023 · 38 citations
- Revisiting Skeleton-based Action RecognitionHaodong Duan, Yue Zhao, Kai Chen, Dahua Lin et al.CVPR 2022 · 752 citations
- Self-Relational Graph Convolution Network for Skeleton-Based Action RecognitionSophyani Banaamwini Yussif, Ning Xie, Yang Yang, Heng Tao ShenACM MM 2023 · 5 citations
- XNect: real-time multi-person 3D motion capture with a single RGB cameraDushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller, Weipeng Xu et al.SIGGRAPH 2020 · 267 citations
- Omni-Scale Feature Learning for Person Re-IdentificationKaiyang Zhou, Yongxin Yang, Andrea Cavallaro, Tao XiangICCV 2019 · 997 citations
