DeepHuMS: Deep Human Motion Signature for 3D Skeletal Sequences
Lecture Notes in Computer Science Pattern Recognition(2020)
摘要
3D Human Motion Indexing and Retrieval is an interesting problem due to the rise of several data-driven applications aimed at analyzing and/or re-utilizing 3D human skeletal data, such as data-driven animation, analysis of sports bio-mechanics, human surveillance etc. Spatio-temporal articulations of humans, noisy/missing data, different speeds of the same motion etc. make it challenging and several of the existing state of the art methods use hand-craft features along with optimization based or histogram based comparison in order to perform retrieval. Further, they demonstrate it only for very small datasets and few classes. We make a case for using a learned representation that should recognize the motion as well as enforce a discriminative ranking. To that end, we propose, a 3D human motion descriptor learned using a deep network. Our learned embedding is generalizable and applicable to real-world data - addressing the aforementioned challenges and further enables sub-motion searching in its embedding space using another network. Our model exploits the inter-class similarity using trajectory cues, and performs far superior in a self-supervised setting. State of the art results on all these fronts is shown on two large scale 3D human motion datasets - NTU RGB+D and HDM05.
更多查看译文
关键词
3D Human Motion Retrieval,Self-supervised learning,4D indexing,MoCap analysis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要