← authors · overview

• CLIP-Adapter: Better Vision-Language Models with Feature Adapters
  2021 · 112 citations
• Contrastive Visual-Linguistic Pretraining
  2020 · 18 citations
• Character Matters: Video Story Understanding with Character-Aware Relations
  2020 · 12 citations
• HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention
  2023 · 11 citations
• A Simple Long-Tailed Recognition Baseline via Vision-Language Model
  2021 · 10 citations
• Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers
  2020 · 4 citations
• Multi-Layer Content Interaction Through Quaternion Product For Visual Question Answering
  2020 · 3 citations
• Frozen CLIP Models are Efficient Video Learners
  2022 · 1 citations
• Dense Contrastive Visual-Linguistic Pretraining
  2021
• COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality
  2021
• Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning
  2022
• Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens
  2023