awesome-self-supervised-multimodal-learning
github.com/ys-zong/awesome-self-supervised-multimodal-learning ↗[T-PAMI] A curated list of self-supervised multimodal learning resources.
278
GitHub Stars
154
Curated Resources
5
Categories
4 hours ago
Last Refreshed
Related Survey PapersObjectivesApplicationsChallengesSummary of Common Multimodal Datasets
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me video-text datasets resources from awesome-self-supervised-multimodal-learning"
Installation instructions →What's inside
Summary of Common Multimodal Datasets
- ActivityNet CaptionsVideo-Text Datasets
20k: 100k
- BreakfastVideo-Text Datasets
-:11267
- CharadesVideo-Text Datasets
10k:10k
- COINVideo-Text Datasets
11,827:-
- CrossTaskVideo-Text Datasets
4.7K:-
- Eigen split KITTTIImage-Ridar Datasets
7481+7518
Objectives
Applications
Showing a sample of 154 resources. View the full list on GitHub →