← authors · overview

• TransTrack: Multiple Object Tracking with Transformer
  2020 · 360 citations
• Language as Queries for Referring Video Object Segmentation
  2022 · 5 citations
• Deformable Tube Network for Action Detection in Videos
  2019 · 3 citations
• Slimmable Generative Adversarial Networks
  2020 · 2 citations
• HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling
  2024 · 2 citations
• HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation
  2025 · 1 citations
• What Makes for End-to-End Object Detection?
  2020 · 1 citations
• Memory Based Video Scene Parsing
  2021 · 1 citations
• MAMO: Masked Multimodal Modeling for Fine-Grained Vision-Language Representation Learning
  2022 · 1 citations
• UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces
  2023 · 1 citations
• NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
  2026
• Bindweave: Subject-consistent Video Generation Via Cross-modal Integration
  2025
• Goku: Flow Based Video Generative Foundation Models
  2025
• Towards Good Practices for Instance Segmentation
  2019
• Towards Grand Unification of Object Tracking
  2022