Fine-grained semantic oriented embedding set alignment for text-based person search

Open Webpage

Jiaqi Zhao, Ao Fu, Yong Zhou, Wen-Liang Du, Rui Yao

Published: 2024, Last Modified: 25 Mar 2026Image Vis. Comput. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•An embedding set alignment module is proposed to extract fine-grained features.•An adaptive semantic margin loss is introduced for text-image alignment adaptively.•Extensive experiments on public benchmarks show our method outperforms the SOTAs.