← authors · overview

• Multimodal Unsupervised Image-to-image Translation
  2018 · 1582 citations
• Occluded Video Instance Segmentation: A Benchmark
  2021 · 133 citations
• Benchmarking Representation Learning For Natural World Image Collections
  2021 · 116 citations
• On Feature Normalization And Data Augmentation
  2020 · 105 citations
• Conditional Similarity Networks
  2016 · 101 citations
• When Does Contrastive Visual Representation Learning Work?
  2021 · 76 citations
• Separating Self-expression And Visual Content In Hashtag Supervision
  2017 · 13 citations
• Large Vision-language Models For Knowledge-grounded Data Annotation Of Memes
  2025
• RAVENEA: A Benchmark For Multimodal Retrieval-augmented Visual Culture Understanding
  2025