@article{Wei_Li_Fan_Xu_Chang_Lyu_2020, title={3D Single-Person Concurrent Activity Detection Using Stacked Relation Network}, volume={34}, url={https://ojs.aaai.org/index.php/AAAI/article/view/6917}, DOI={10.1609/aaai.v34i07.6917}, abstractNote={<p>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 <em>decompositional design</em> 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/</p>}, number={07}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wei, Yi and Li, Wenbo and Fan, Yanbo and Xu, Linghan and Chang, Ming-Ching and Lyu, Siwei}, year={2020}, month={Apr.}, pages={12329-12337} }