metadata
license: mit
datasets:
- conceptual_captions
- sbu_captions
- visual_genome
language:
- en
tags:
- ManagerTower
Model weights for ACL 2023 Oral Paper: ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning.
Additional materials: Code, Slides, Video(EN), Video(CN), Blog(CN), Tweet(EN).