Pinned Loading

1. showlab/Image2Paragraph showlab/Image2Paragraph Public

   [Image 2 Text Para] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.

   Python 825 56

2. showlab/all-in-one showlab/all-in-one Public

   [CVPR2023] All in One: Exploring Unified Video-Language Pre-training

   Python 281 19

3. BE BE Public

   [CVPR2021] The source code for our paper 《Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning》.

   Python 135 11

4. DSM-decoupling-scene-motion DSM-decoupling-scene-motion Public

   [AAAI2021] The source code for our paper 《Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion》.

   Python 97 4

5. sail-sg/ptp sail-sg/ptp Public

   [CVPR2023] The code for 《Position-guided Text Prompt for Vision-Language Pre-training》

   Python 151 4

6. sail-sg/EditAnything sail-sg/EditAnything Public

   Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

   Python 3.4k 199