Advancing Visible-Infrared Person Re-Identification: Synergizing Visual-Textual Reasoning and Cross-Modal Feature Alignment

计算机科学 特征(语言学) 情态动词 鉴定(生物学) 人工智能 特征提取 模式识别(心理学) 计算机视觉 语音识别 哲学 语言学 植物 化学 高分子化学 生物
作者
Yuxuan Qiu,Liyang Wang,Wei Song,Jiawei Liu,Zhiping Shi,Na Jiang
出处
期刊:IEEE Transactions on Information Forensics and Security [Institute of Electrical and Electronics Engineers]
卷期号:20: 2184-2196 被引量:27
标识
DOI:10.1109/tifs.2025.3539946
摘要

Visible-infrared person re-identification (VI-ReID) is a critical cross-modality fine-grained classification task with significant implications for public safety and security applications. Existing VI-ReID methods primarily focus on extracting modality-invariant features for person retrieval. However, due to the inherent lack of texture information in infrared images, these modality-invariant features tend to emphasize global contexts. Consequently, individuals with similar silhouettes are often misidentified, posing potential risks to security systems and forensic investigations. To address this problem, this paper innovatively introduces natural language descriptions to learn the global-local contexts for VI-ReID. Specifically, we design a framework that jointly optimizes visible-infrared alignment plus (VIAP) and visual-textual reasoning (VTR), and introduces local-global joint measure (LJM) to enhance the metric, while proposing a human-LLM collaborative approach to incorporate textual descriptions into existing cross-modal person re-identification datasets. VIAP achieves cross-modal alignment between RGB and IR. It can explicitly utilize designed frequency-aware modality alignment and relationship-reinforced fusion to explore the potential of local cues in global features and modality-invariant information. VTR proposes pooling selection and dual-level reasoning mechanisms to force the image encoder to pay attention to significant regions based on textual descriptions. LJM proposes introducing local feature distances into the measure stage metric to enhance the relevance of matching using fine-grained information. Extensive experimental results on the popular SYSU-MM01 and RegDB datasets show that the proposed method significantly outperforms state-of-the-art approaches. The dataset is publicly available athttps://github.com/qyx596/vireid-caption.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
刚刚
刚刚
所所的应助被April采纳,获得10
2秒前
2秒前
丘比特的应助被江南达尔贝采纳,获得10
2秒前
李爱国的应助被RoseTaurus采纳,获得30
3秒前
3秒前
豆子发布了新的文献求助10
4秒前
隐形曼青的应助被勤恳依秋采纳,获得10
4秒前
Jasper的应助被广府何家大少爷采纳,获得10
4秒前
5秒前
5秒前
采一发布了新的文献求助10
5秒前
关耳完成签到 ,获得积分20
5秒前
小张发布了新的文献求助10
5秒前
香蕉觅云的应助被晴满空_采纳,获得10
5秒前
斯文败类的应助被xc采纳,获得30
6秒前
6秒前
大模型的应助被xc采纳,获得10
6秒前
无花果的应助被xc采纳,获得10
6秒前
大模型的应助被xc采纳,获得10
6秒前
6秒前
鹅蛋脸发布了新的文献求助10
7秒前
iceicefdtd发布了新的文献求助10
7秒前
pp完成签到,获得积分10
7秒前
瑶啊瑶完成签到,获得积分10
7秒前
7秒前
wangdongyue1987完成签到,获得积分20
7秒前
Orange的应助被喷火龙采纳,获得10
7秒前
8秒前
9秒前
逍遥游233完成签到 ,获得积分10
9秒前
siraotianya完成签到,获得积分10
10秒前
w0304hf发布了新的文献求助10
11秒前
11秒前
abcde发布了新的文献求助10
11秒前
12秒前
ding的应助被健壮的化蛹采纳,获得30
12秒前
yy关注了科研通微信公众号
12秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8194239
求助须知:如何正确求助?哪些是违规求助? 9580103
关于积分的说明 21869458
捐赠科研通 7793840
什么是DOI,文献DOI怎么找? 3437562
关于科研通互助平台的介绍 2560983
邀请新用户注册赠送积分活动 2484332