https://github.com/x-plug/mplug
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections. (EMNLP 2022)
https://github.com/x-plug/mplug
image-captioning image-text image-text-retrieval multimodal pretraining pytorch transformer visual-language vqa
Last synced: 4 months ago
JSON representation
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections. (EMNLP 2022)
- Host: GitHub
- URL: https://github.com/x-plug/mplug
- Owner: X-PLUG
- Created: 2023-05-08T07:32:30.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-05-08T07:45:16.000Z (over 2 years ago)
- Last Synced: 2025-05-30T12:20:25.634Z (4 months ago)
- Topics: image-captioning, image-text, image-text-retrieval, multimodal, pretraining, pytorch, transformer, visual-language, vqa
- Language: Python
- Homepage: https://arxiv.org/abs/2205.12005
- Size: 1.56 MB
- Stars: 91
- Watchers: 2
- Forks: 8
- Open Issues: 11