Sanping Zhou

18

Papers

60

Total Citations

Papers (18)

Towards Generalizable Multi-Object Tracking

PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation

FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation

Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding

AugDETR: Improving Multi-scale Learning for Detection Transformer

DAMap: Distance-aware MapNet for High Quality HD Map Construction

Enhancing Mamba Decoder with Bidirectional Interaction in Multi-Task Dense Prediction

Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion

REGNav: Room Expert Guided Image-Goal Navigation

RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension

Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection

Temporal Correlation Vision Transformer for Video Person Re-Identification

FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers

PDFactor: Learning Tri-Perspective View Policy Diffusion Field for Multi-Task Robotic Manipulation

Event-Equalized Dense Video Captioning

Boosting Point-Supervised Temporal Action Localization through Integrating Query Reformation and Optimal Transport

Moment Quantization for Video Temporal Grounding

Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching