PPaperPicks

Lechao Cheng

28 papers at tracked venues · 20 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning
  2. A Large-scale Universal Evaluation Benchmark For Face Forgery Detection
  3. ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding
  4. Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations
  5. Beyond General Alignment: Fine-Grained Entity-Centric Image-Text Matching with Multimodal Attentive Experts
  6. DCP: Dual-Cue Pruning for Efficient Large Vision-Language Models
  7. Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observations
  8. Efficient Vision Language Model Fine-tuning for Text-based Person Anomaly Search
  9. FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adapter
  10. Knowledge Swapping via Learning and Unlearning
  11. Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
  12. SLRTP2025 Sign Language Production Challenge: Methodology, Results and Future Work
  13. STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery Identification
  14. Self-Classification Enhancement and Correction for Weakly Supervised Object Detection
  15. Shaping a Stabilized Video by Mitigating Unintended Changes for Concept-Augmented Video Editing
  16. Spoofing-aware Prompt Learning for Unified Physical-Digital Facial Attack Detection
  17. Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach
  18. 3D-GOI: 3D GAN Omni-Inversion for Multifaceted and Multi-object Editing
  19. Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
  20. GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding
  21. Improving Knowledge Distillation via Regularizing Feature Direction and Norm
  22. Instance-Aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning
  23. LoopGaussian: Creating 3D Cinemagraph with Multi-view Images via Eulerian Motion Field
  24. MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection
  25. Open-Vocabulary Video Relation Extraction
  26. Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation
  27. Revisiting the Power of Prompt for Visual Tuning
  28. ViT-Calibrator: Decision Stream Calibration for Vision Transformer