Weizhen He — accepted AI-conference papers

2024

Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions

Weizhen He, Yiheng Deng, Shixiang Tang, Qihao Chen, Qingsong Xie, Yizhou Wang +6

CVPR 2024poster

Human intelligence can retrieve any person according to both visual and language descriptions. However the current computer vision community studies specific person re-identification (ReID) tasks in different scenarios separately which limits the applications in the real world. This paper strives to…

Cited by 26 Source ↗PDF ↗code ↗Scholar ↗

2023

Unsupervised Prompt Tuning for Text-Driven Object Detection

Weizhen He, Weijie Chen, Binbin Chen, Shicai Yang, Di Xie, Luojun Lin +2

ICCV 2023poster

Grounded language-image pre-trained models have shown strong zero-shot generalization to various downstream object detection tasks. Despite their promising performance, the models rely heavily on the laborious prompt engineering. Existing works typically address this problem by tuning text prompts u…

Cited by 9 PDF ↗Scholar ↗