 AM-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action RecognitionInternational Journal of Computer Vision (IJCV), 2025 |
 Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?Social Science Research Network (SSRN), 2025 |
 Active Multimodal Distillation for Few-shot Action RecognitionInternational Joint Conference on Artificial Intelligence (IJCAI), 2025 |
 DejaVid: Encoder-Agnostic Learned Temporal Matching for Video ClassificationComputer Vision and Pattern Recognition (CVPR), 2025 |
An Effective End-to-End Solution for Multimodal Action RecognitionInternational Conference on Pattern Recognition (ICPR), 2025 |
 |
 VidEvent: A Large Dataset for Understanding Dynamic Evolution of Events in VideosAAAI Conference on Artificial Intelligence (AAAI), 2025 |
