Frequency-enhanced diffusion models: curriculum-guided semantic alignment for zero-shot skeleton action recognition

The Visual Computer 2026

View at publisher

Authors: Yuxi Zhou, Zhengbo Zhang, Jingyu Pan, Zhiyu Lin, Zhigang Tu

DOI: 10.1007/s00371-026-04522-x

Cited by: 1

References: 57

Fields of Study & Subjects

Human Pose and Action Recognition Human Motion and Animation Domain Adaptation and Few-Shot Learning

References 57