https://github.com/daveredrum/d3net
[ECCV2022] D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding
https://github.com/daveredrum/d3net
3d caption-generation computer-vision deep-learning eccv eccv2022 natural-language-processing point-cloud semi-supervised-learning visual-grounding
Last synced: 8 months ago
JSON representation
[ECCV2022] D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding
- Host: GitHub
- URL: https://github.com/daveredrum/d3net
- Owner: daveredrum
- Created: 2021-11-30T14:35:30.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2022-08-27T08:07:32.000Z (almost 4 years ago)
- Last Synced: 2024-04-21T10:25:42.310Z (about 2 years ago)
- Topics: 3d, caption-generation, computer-vision, deep-learning, eccv, eccv2022, natural-language-processing, point-cloud, semi-supervised-learning, visual-grounding
- Language: Python
- Homepage: https://daveredrum.github.io/D3Net/
- Size: 105 MB
- Stars: 36
- Watchers: 2
- Forks: 5
- Open Issues: 5