2 papers
cs.CV2026
Intra-Modal Neighbors Never Lie: Rectifying Inter-Modal Noisy Correspondence via Graph-Based Intra-Modal Reasoning
Yang Liu, Wentao Feng, Shu-Dong Huang +2
Large-scale web-harvested datasets have fueled the progress of cross-modal retrieval but inevitably suffer from noisy correspondence, which severely degrades model generalization.…
cs.CV2026
SkeFi: Cross-Modal Knowledge Transfer for Wireless Skeleton-Based Action Recognition
Shunyu Huang, Yunjiao Zhou, Jianfei Yang
Skeleton-based action recognition leverages human pose keypoints to categorize human actions, which shows superior generalization and interoperability compared to regular end-to-en…