PPaperPicks

Hong Liu

Peking University, Shenzhen Graduate School, Key Laboratory of Machine Perception, Engineering Lab on Intelligent Perception for Internet of Things, Beijing, China

16 papers at tracked venues · 12 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Debiased Multiplex Tokenizer for Efficient Map-Free Visual Relocalization
  2. Masked Clustering Prediction for Unsupervised Point Cloud Pre-training
  3. A Unified End-to-End Network for Category-Level and Instance-Level Object Pose Estimation from RGB Images
  4. CLIP-6D: Empowering CLIP as a Zero-Shot 6D Pose Estimator Through Generalizable Object-Specific Representations
  5. PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes
  6. PRIDEV: A Plug-and-Play Refinement for Improved Depth Estimation in Videos
  7. Recognizing Actions From Robotic View for Natural Human-Robot Interaction
  8. SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation
  9. TCNet: A Temporally Consistent Network for Self-supervised Monocular Depth Estimation
  10. TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation
  11. UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling
  12. APP: Adaptive Pose Pooling for 3D Human Pose Estimation from Videos
  13. ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos
  14. ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models
  15. Dual-Branch Graph Transformer Network for 3D Human Mesh Reconstruction from Video
  16. Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation