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
• Toward an end-to-end implicit addressee modeling for dialogue disentanglement
• iDAT: inverse Distillation Adapter-Tuning
• Toward an end-to-end implicit addressee modeling for dialogue disentanglement
• Editing outdoor scenes with a large annotated synthetic dataset
• Learning to Floorplan like Human Experts via Reinforcement Learning
• Deep multimodal representation learning for generalizable person re-identification
• Rethinking person re-identification via semantic-based pretraining
• Ege-unet: an efficient group enhanced unet for skin lesion segmentation
• DynaSlim: Dynamic Slimming for Vision Transformers
• AV-TAD: Audio-Visual Temporal Action Detection with Transformer
• CC-PoseNet: Towards human pose estimation in crowded classrooms
• MALUNet: A Multi-Attention and Light-weight UNet for Skin Lesion Segmentation
• Spatial Attention Guided Local Facial Attribute Editing
• GOS: A Large-Scale Annotated Outdoor Scene Synthetic Dataset
• SynPose: A Large-scale and Densely Annotated Synthetic Dataset for Human Pose Estimation in Classroom
• DFFCN: Dual Flow Fusion Convolutional Network for Micro Expression Recognition
• Dynamic Channel Pruning for Real-Time Object Detection Networks
• Improving Abstractive Dialogue Summarization with Hierarchical Pretraining and Topic Segment
• Taking A Closer Look at Synthesis: Fine-Grained Attribute Analysis for Person Re-Identification
• Attribute analysis with synthetic dataset for person re-identification
• Deep unsupervised progressive learning for distant domain adaptation