awesome-clip-papers

The most impactful papers related to contrastive pretraining for multimodal models!
https://github.com/jacobmarks/awesome-clip-papers

Last synced: about 1 month ago
JSON representation

CLIP + Additional Pretraining Objectives

![arXiv
![arXiv - full#:~:text=License%3A,bsd%2D3%2Dclause) |
![arXiv
![arXiv
![arXiv
![arXiv
![arXiv - mobileclip/blob/main/LICENSE) |

Contrastive Language-Image Pretraining (CLIP)

![arXiv - card.md) | ✔️ |
![arXiv - base) | ❌ |
![arXiv - jku/cloob?style=social)](https://github.com/ml-jku/cloob) | ✔️ | License | | ❌ |
![arXiv - GVT/DeCLIP?style=social)](https://github.com/Sense-GVT/DeCLIP) | ✔️ | License | | ❌ |
![arXiv
![arXiv - GVT/DeCLIP?style=social)](https://github.com/Sense-GVT/DeCLIP) | ✔️ | License | | ❌ |
![arXiv
![arXiv
![arXiv - shashank/CyCLIP?style=social)](https://github.com/goel-shashank/CyCLIP) | ✔️ | License | | ❌ |
![arXiv
![arXiv
![arXiv - CLIP) | ✔️ | | Model Card | ✔️ |
![arXiv - research/big_vision?style=social)](https://github.com/google-research/big_vision) | ✔️ | License | | ✔️ |
![arXiv - VLAA/CLIPA?style=social)](https://github.com/UCSC-VLAA/CLIPA) | ✔️ | License | | ✔️ |
![arXiv
![arXiv - CLIP-ViT-H-14-378/blob/main/LICENSE) | Model Card | ✔️ |

Contrastive Pretraining for Other Modalities

3D

Audio

![arXiv
![arXiv - wav2clip?style=social)](https://github.com/descriptinc/lyrebird-wav2clip) | ✔️ | License |
![arXiv
![arXiv - AI/CLAP?style=social)](https://github.com/LAION-AI/CLAP) | ✔️ | License |
![arXiv - tts?style=social)](https://github.com/neonbjb/tortoise-tts) | ✔️ | License |

Video

![arXiv - CLIP?style=social)](https://github.com/xuguohai/X-CLIP) | ✔️ | License |
![arXiv