Text-Guided Visual Representation Learning via Cross-Modal Fusion for Person Re-Identification
Open Access
- 30 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 114911-114922
Abstract
Person Re-identification (Re-ID) aims at accurately querying pedestrians across multiple non-overlapping cameras system, playing an essential role in computer vision applications. While CNN-based methods leverage feature aggregation and attention mechanisms to achieve competitive performance, their limitations in capturing long-range dependencies have motivated the research of transformer-based architectures, which excel in the evolution of person Re-ID research. Despite leveraging pretrained vision-language models to facilitate visual encoder training, current methods suffer from fragmented optimization procedures, complexity increasing, and inadequate semantic guidance from textual prompts. To address these limitations, we propose an end-to-end method named Text-Guided Fusion Transformer (TGFT). TGFT applies the fixed but semantically enriched texts to guide visual training with a novel Gated Cross Attention (GCA) fusion module. The GCA module adaptively modulates the integration of textual information and visual features, effectively enhancing cross-modal feature alignment and semantic consistency. Without significantly increasing computational complexity or parameter count, TGFT achieves superior performance, demonstrating strong effectiveness and scalability on multiple major Re-ID benchmarks.Keywords
Funding Information
- “Regional Innovation System and Education (RISE)” through the Ulsan RISE Center
- Ministry of Education
- Ulsan Metropolitan City, Republic of Korea (2025-RISE-07-001)
This publication has 45 references indexed in Scilit:
- Cluster Contrast for Unsupervised Person Re-identification2023
- Learning to Prompt for Vision-Language ModelsInternational Journal of Computer Vision, 2022
- Fully Unsupervised Person Re-Identification via Multiple Pseudo Labels Joint TrainingIEEE Access, 2021
- Identity-Guided Human Semantic Parsing for Person Re-identification2020
- Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification2019
- Person Transfer GAN to Bridge Domain Gap for Person Re-identification2018
- Unsupervised Feature Learning via Non-parametric Instance Discrimination2018
- Re-ranking Person Re-identification with k-Reciprocal Encoding2017
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009