
Title |
|---|
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language ModelsComputer Vision and Pattern Recognition (CVPR), 2025 |
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet
VideosNeural Information Processing Systems (NeurIPS), 2024 |
![]() TSAK: Two-Stage Semantic-Aware Knowledge Distillation for Efficient
Wearable Modality and Model Optimization in Manufacturing LinesInternational Conference on Pattern Recognition (ICPR), 2024 |