yanbinhao

Latest

• Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
• Selective Vision-Language Subspace Projection for Few-shot CLIP
• Boosting Few-shot Learning via Attentive Feature Regularization
• CgT-GAN: CLIP-guided Text GAN for Image Captioning
• Semantic-based Selection, Synthesis, and Supervision for Few-shot Learning
• Bi-directional Distribution Alignment for Transductive Zero Shot Learning
• Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
• Hierarchical Hourglass Convolutional Network for Efficient Video Classification
• Multi-directional Knowledge Transfer for Few-Shot Learning
• Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP
• Unsupervised Video Hashing with Multi-granularity Contextualization and Multi-structure Preservation
• Group Contextualization for Video Recognition
• Attention in Attention: Modeling Context Correlation for Efficient Video Classification
• Selective Dependency Aggregation for Action Classification