Changxin Gao

Full Professor@Huazhong University of Science and Technology·中国·OpenReview

研究方向

Collaborative Perception · text-image person retrieval · scene understanding; semantic segmentation · person search · identification; video intelligent analysis

Changxin Gao

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment

ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model

Continual Gaussian Mixture Distribution Modeling for Class Incremental Semantic Segmentation

VideoLucy: Deep Memory Backtracking for Long Video Understanding

Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts

MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane Representation

Towards Reliable and Holistic Visual In-Context Learning Prompt Selection