← authors · overview

• Oscar: Object-semantics Aligned Pre-training For Vision-language Tasks
  2020 · 989 citations
• Vinvl: Revisiting Visual Representations In Vision-language Models
  2021 · 712 citations
• Rethinking Classification And Localization For Object Detection
  2019 · 601 citations
• An Empirical Study Of Training End-to-end Vision-and-language Transformers
  2021 · 273 citations
• Scaling Up Vision-language Pre-training For Image Captioning
  2021 · 157 citations
• M3P: Learning Universal Representations Via Multitask Multilingual Multimodal Pre-training
  2020 · 52 citations
• Equivariant Similarity For Vision-language Foundation Models
  2023 · 18 citations
• Coarse-to-fine Vision-language Pre-training With Fusion In The Backbone
  2022 · 10 citations
• UFO: A Unified Transformer For Vision-language Representation Learning
  2021
• Interfacing Foundation Models' Embeddings
  2023