PPaperPicks

Ge Li

Peking University Shenzhen Graduate School, School of Electronic and Computer Engineering, Shenzhen, China

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

Venues

Frequent coauthors

Papers

  1. Video Spatial Reasoning with Object-Centric 3D Rollout
  2. AI-based Multimedia Data Compression: Perception Utility Optimization and Standardization
  3. APP3DV'25: ACM Multimedia - International Workshop on Application-driven Point Cloud Processing and 3D Vision
  4. DGTalker: Disentangled Generative Latent Space Learning for Audio-Driven Gaussian Talking Heads
  5. Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow
  6. MUSE: Mamba Is Efficient Multi-scale Learner for Text-video Retrieval
  7. Overfitted Point Cloud Attribute Codec Using Sparse Hierarchical Implicit Neural Representations
  8. Point Cloud Semantic Segmentation with Sparse and Inhomogeneous Annotations
  9. Stochasticity-aware No-Reference Point Cloud Quality Assessment
  10. BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning
  11. Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation
  12. Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection
  13. Less Is More: Label Recommendation for Weakly Supervised Point Cloud Semantic Segmentation
  14. Point Cloud Compression, Enhancement and Applications: From 3D Perception to Large Models
  15. RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter
  16. ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision
  17. SPCGC: Scalable Point Cloud Geometry Compression for Machine Vision
  18. ST-LLM: Large Language Models Are Effective Temporal Learners
  19. ViewPCGC: View-Guided Learned Point Cloud Geometry Compression