LV-ReID: Large Language-Vision Alignment Model for Text-based Person Re-identification
Yinghui Xia, Chao Wang, Jinsong Yang
Abstract
Person Re-Identification (ReID) is a critical task in computer vision that involves identifying individuals across different cameras or video frames. It’s challenging due to variations in appearance, lighting, viewpoints, clothing, and occlusions. Text-based ReID adds complexity by requiring image retrieval or individual identification from a dataset based on text queries. The BLIP-2 model addresses these challenges by combining multi-modal alignment and matching into a single framework, using a pre-trained vision-language model with a Q-Former component to bridge the visual and textual modalities. This approach significantly boosts performance in multi-modal tasks and information retrieval, especially with large datasets. The LV-ReID framework, which incorporates BLIP-2, enhances text-based ReID by integrating retrieval and generation tasks. The experimental results show BLIP-2’s effectiveness in aligning and matching pedestrian images for information retrieval tasks. It demonstrates proficiency in multi-modal tasks and offers an efficient solution for text-based ReID by fusing visual and textual data, improving pedestrian identification accuracy in complex environments.
BibTeX
@inproceedings{icassp2025_lvreidlargelangu,
title = {LV-ReID: Large Language-Vision Alignment Model for Text-based Person Re-identification},
author = {Yinghui Xia and Chao Wang and Jinsong Yang},
booktitle = {ICASSP 2025},
year = {2025}
}