3 papers
cs.CV2026
Zero-Gated Language-conditioned Human Motion Prediction
Guanhui Qiao, Lu Zhou, Ding Jiang +1
Pose histories provide the core kinematic evidence for 3D human motion prediction, but they lack explicit high-level semantic guidance. This paper introduces ZGL, a lightweight lan…
cs.SD2026
Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning
Linge Wang, Yingying Chen, Bingke Zhu +2
Recent advances in audio-visual representation learning have shown the value of combining contrastive alignment with masked reconstruction. However, jointly optimizing these object…
cs.CV2023
Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition
Jinzhao Luo, Lu Zhou, Guibo Zhu +3
Skeleton-based action recognition has become popular in recent years due to its efficiency and robustness. Most current methods adopt graph convolutional network (GCN) for topology…