PPaperPicks

Kun Li

Hefei University of Technology, School of Computer Science and Information Engineering, China

19 papers at tracked venues · 16 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. DLVINet: Advancing Dual-Lens Video Inpainting Beyond Parallax Constraints
  2. GraphTARIF: Linear Graph Transformer with Augmented Rank and Improved Focus
  3. XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being
  4. BVINet: Unlocking Blind Video Inpainting With Zero Annotations
  5. Drafting and Revision: Advancing High-Fidelity Video Inpainting
  6. Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning
  7. Exploiting Ensemble Learning for Cross-View Isolated Sign Language Recognition
  8. MAC 2025: The 2nd Micro-Action Analysis Grand Challenge
    ACM MM 2025 · Kun Li
  9. MMAD: Multi-Label Micro-Action Detection in Videos
    ICCV 2025 · Kun Li
  10. Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition
  11. Patch-level Sounding Object Tracking for Audio-Visual Question Answering
  12. Prompt-Aware Controllable Shadow Removal
  13. Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition
    AAAI 2025 · Kun Li
  14. ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning
  15. Cluster-Phys: Facial Clues Clustering Towards Efficient Remote Physiological Measurement
  16. EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer
  17. Frequency Decoupling for Motion Magnification Via Multi-Level Isomorphic Architecture
  18. MAC 2024: Micro-Action Analysis Grand Challenge
  19. Maskable Retentive Network for Video Moment Retrieval