3 papers
cs.CV2026
Exploring Adaptive Masked Reconstruction for Self-Supervised Skeleton-Based Action Recognition
Shengkai Sun, Zhiyong Cheng, Zefan Zhang +3
Recently, masked skeleton reconstruction models have emerged as strong action representation learners, driving significant progress in self-supervised skeleton-based action recogni…
cs.CV2025
Towards Efficient General Feature Prediction in Masked Skeleton Modeling
Shengkai Sun, Zefan Zhang, Jianfeng Dong +3
Recent advances in the masked autoencoder (MAE) paradigm have significantly propelled self-supervised skeleton-based action recognition. However, most existing approaches limit rec…
cs.CV2025
Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation
Jinxing Zhou, Zhihui Li, Yongqiang Yu +7
We present \textbf{Met}a-\textbf{T}oken \textbf{Le}arning (Mettle), a simple and memory-efficient method for adapting large-scale pretrained transformer models to downstream audio-…