最新

• GIST: Improving Parameter Efficient Fine Tuning via Knowledge Interaction
• From Raw Video to Pedagogical Insights: A Unified Framework for Student Behavior Analysis
• LAMM: Label Alignment for Multi-Modal Prompt Learning
• Learning to Floorplan like Human Experts via Reinforcement Learning
• Deep multimodal representation learning for generalizable person re-identification
• AV-TAD: Audio-Visual Temporal Action Detection with Transformer
• CC-PoseNet: Towards human pose estimation in crowded classrooms
• SynPose: A Large-scale and Densely Annotated Synthetic Dataset for Human Pose Estimation in Classroom