Towards more realistic human motion prediction with attention to motion coordination

arXiv:2404.03584v1 Announce Type: new
Abstract: Joint relation modeling is a curial component in human motion prediction. Most existing methods rely on skeletal-based graphs to build the joint relations, where local interactive relations between joint pairs are well learned. However, the motion coordination, a global joint relation reflecting the simultaneous cooperation of all joints, is usually weakened because it is learned from part to whole progressively and asynchronously. Thus, the final predicted motions usually appear unrealistic. To tackle this issue, we …

abstract arxiv attention build cs.cv global graphs however human interactive modeling prediction relations type