← authors · overview

• DOLG: Single-stage Image Retrieval With Deep Orthogonal Fusion Of Local And Global Features
  2021 · 133 citations
• Vista: Vision And Scene Text Aggregation For Cross-modal Retrieval
  2022 · 80 citations
• CODER: Coupled Diversity-sensitive Momentum Contrastive Learning For Image-text Retrieval
  2022 · 27 citations
• Boosting Video-text Retrieval With Explicit High-level Semantics
  2022 · 9 citations
• Understanding Image Retrieval Re-ranking: A Graph Neural Network Perspective
  2020