Progressive Semantic Learning for Unsupervised Skeleton-based Action Recognition

Feb 6, 2025·
秦皓
秦皓
,
Luyuan Chen
,
Ming Kong
,
Zhuoran Zhao
,
Xianzhou Zeng
,
Mengxu Lu
,
Qiang Zhu
· 1 min read
Abstract
ProSL progressively optimizes pseudo-label generation in self-supervised contrastive learning for skeleton-based action recognition. It builds a semantic codebook from clustering and iteratively improves representation learning on multiple downstream tasks.
Type
Publication
Machine Learning
publications

ProSL uses cluster-level semantic information to improve self-supervised skeleton representation learning beyond instance-level contrastive objectives.

Self-Supervised Learning Action Recognition Skeleton-Based Recognition
秦皓
Authors
秦皓
Ph.D. Student at Zhejiang University

I am a Ph.D. student in the College of Computer Science and Technology at Zhejiang University. My research focuses on spatial intelligence, 3D-AIGC, multi-agent systems, latent reasoning for VLMs, and contrastive learning, with a broader interest in building intelligent systems that connect perception, reasoning, and controllable creation in the world.

Email: haoqin@zju.edu.cn