Zheng Qin

13

Papers

79

Total Citations

Papers (13)

Multi-Prompts Learning with Cross-Modal Alignment for Attribute-Based Person Re-identification

Towards Generalizable Multi-Object Tracking

Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes

Multi-Modal Relational Graph for Cross-Modal Video Moment Retrieval

Geometric Transformer for Fast and Robust Point Cloud Registration

MotionTrack: Learning Robust Short-Term and Long-Term Motions for Multi-Object Tracking

Rotation-Invariant Transformer for Point Cloud Matching

Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration

ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices

Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion

2D3D-MATR: 2D-3D Matching Transformer for Detection-Free Registration Between Images and Point Clouds

CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs

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