← authors · overview

• Improved Deep Hashing With Soft Pairwise Similarity For Multi-label Image Retrieval
  2018 · 174 citations
• Lingoqa: Visual Question Answering For Autonomous Driving
  2023 · 130 citations
• Cross-view Tracking For Multi-human 3D Pose Estimation At Over 100 FPS
  2020 · 79 citations
• Carllava: Vision Language Models For Camera-only Closed-loop Driving
  2024 · 67 citations
• Lightweight Single-image Super-resolution Network With Attentive Auxiliary Feature Learning
  2020 · 49 citations
• Centernet3d: An Anchor Free Object Detector For Point Cloud
  2020 · 38 citations
• Unipt: Universal Parallel Tuning For Transfer Learning With Efficient Parameter And Memory
  2023 · 31 citations
• SCHEMA: State Changes Matter For Procedure Planning In Instructional Videos
  2024 · 26 citations
• A Comprehensive Survey Of Direct Preference Optimization: Datasets, Theories, Variants, And Applications
  2024 · 24 citations
• Transductive Zero-shot Hashing For Multilabel Image Retrieval
  2019 · 14 citations
• Sortedap: Rethinking Evaluation Metrics For Instance Segmentation
  2023 · 13 citations
• Improving Pixel Embedding Learning Through Intermediate Distance Regression Supervision For Instance Segmentation
  2020 · 7 citations
• GSSF: Generalized Structural Sparse Function For Deep Cross-modal Metric Learning
  2024 · 5 citations
• Vquala 2025 Challenge On Engagement Prediction For Short Videos: Methods And Results
  2025 · 3 citations
• Mimo-embodied: X-embodied Foundation Model Technical Report
  2026