PolyU survey unifies fragmented human-centric AI research with a six-layer progressive framework

jiqizhixin · x · 2026-09-15

A Hong Kong Polytechnic University team led by Prof. Jingcai Guo releases a comprehensive survey arguing that human-centric AI research is fragmented across body attribute perception, 3D structure recovery, motion capture, human-object interaction reasoning, world dynamics prediction, and embodied experience transfer. The survey organizes the field into six progressively expanding layers: (1) perceiving/generating human visual attributes, (2) recovering/understanding human spatial structure, (3) capturing/generating human motion, (4) reasoning/generating human-environment interaction, (5) predicting human-centric world dynamics, and beyond — offering a unified conceptual modeling framework.

Original post →

More from Research

Research channel →