Hongshen Zhao — accepted AI-conference papers

2025

Mamba-Adaptor: State Space Model Adaptor for Visual Recognition

Fei Xie, Jiahao Nie, Yujin Tang, Wenkang Zhang, Hongshen Zhao

CVPR 2025poster

Recent State Space Models (SSM), especially Mamba, have demonstrated impressive performance in visual modeling and possess superior model efficiency. However, the application of Mamba to visual tasks suffers inferior performance due to three main constraints existing in the sequential model: 1) Casu…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination

Ming Dai, Wenxuan Cheng, Jiedong Zhuang, Jiang-jiang Liu, Hongshen Zhao, Zhenhua Feng +1

ICCV 2025poster

Recent advances in visual grounding have largely shifted away from traditional proposal-based two-stage frameworks due to their inefficiency and high computational complexity, favoring end-to-end direct reference paradigms. However, these methods rely exclusively on the referred target for supervisi…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗