Research domain

Retrieval

1. Learning Transferable Visual Models From Natural Language Supervision Paper Code
2. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision Paper
3. Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation Paper
4. Better Vision-Language Models with Feature Adapters Paper Code

Detection&Segmentation

1. A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model Paper Code
2. Open-vocabulary Object Detection via Vision and Language Knowledge Distillation Paper Code

Caption

1. CLIP for Video Caption Paper