PPaperPicks

Zhongyuan Wang

Wuhan University, School of Computer Science, Wuhan, China

16 papers at tracked venues · 14 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. DeformTrace: A Deformable State Space Model with Relay Tokens for Temporal Forgery Localization
  2. GLoMOT: Efficient Online GNN-based Low-Frame-Rate Multi-Object Tracker
  3. Rethinking Surgical Smoke: A Smoke-Type-Aware Laparoscopic Video Desmoking Method and Dataset
  4. Cross-Modal Stealth: A Coarse-to-Fine Attack Framework for RGB-T Tracker
  5. FriendsQA: A New Large-Scale Deep Video Understanding Dataset with Fine-grained Topic Categorization for Story Videos
  6. Link-based Contrastive Learning for One-Shot Unsupervised Domain Adaptation
  7. Multi-Shape Matching with Cycle Consistency Basis via Functional Maps
  8. OODML: Whole Slide Image Classification Meets Online Pseudo-Supervision and Dynamic Mutual Learning
  9. ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for Mllm-Based Process Judges
  10. Quantum Interference-Inspired Who-What-Where Composite-Semantics Instance Search for Story Videos
  11. Query-Based Audio-Visual Temporal Forgery Localization with Register-Enhanced Representation Learning
  12. Rethinking the Adversarial Robustness of Multi-Exit Neural Networks in an Attack-Defense Game
  13. Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection
  14. Can We Leave Deepfake Data Behind in Training Deepfake Detector?
  15. Exploring Sentence Type Effects on the Lombard Effect and Intelligibility Enhancement: A Comparative Study of Natural and Grid Sentences
  16. Refining Intraocular Lens Power Calculation: A Multi-modal Framework Using Cross-Layer Attention and Effective Channel Attention