激光与光电子学进展, 2024, 61 (10): 1015001, 网络出版: 2024-04-02   

基于掩模重构与动态注意力的跨模态行人重识别 下载: 682次【增强内容出版】

Cross-Modal Person Re-Identification Based on Mask Reconstruction with Dynamic Attention
作者单位
重庆邮电大学通信与信息工程学院,重庆 400065
摘要
跨模态行人重识别是一项具有挑战性的行人检索任务。现有研究侧重于通过提取模态共享特征来减小模态间差异,忽视了对模态内差异和背景干扰的处理。为此,提出了一种掩模重构与动态注意力(MRDA)网络,该网络通过重构人体区域特征来消除背景杂波的影响,从而增强网络对背景变化的鲁棒性。此外,该网络结合了动态注意力机制,以过滤无关信息,动态挖掘并增强具有辨别力的特征表示,消除模态内差异的影响。实验结果显示:该网络在SYSU-MM01数据集的all-search模式下的第一个检索结果匹配成功的概率(Rank-1)和均值平均精度(mAP)分别达到70.55%和63.89%;在RegDB数据集的visible-to-infrared检索模式下的Rank-1和mAP分别达到91.80%和82.08%。在公共数据集上验证了所提方法的有效性。
Abstract
Cross-modal person re-identification is a challenging pedestrian retrieval task. Existing research focuses on reducing inter-modal differences by extracting modal shared features, while ignoring the processing of intra-modal differences and background interference. In this regard, a mask reconstruction and dynamic attention (MRDA) network is proposed to eliminate the influence of background clutter by reconstructing the features of human body regions, thereby enhancing the robustness of the network on background changes. In addition, the dynamic attention mechanism is combined to filter irrelevant information, dynamically mine and enhance the discriminating feature representations, and eliminate the influence of intra-modal differences. The experimental results show that the probability the first search result matches successfully (Rank-1) and mean average precision (mAP) in the all-search mode of the SYSU-MM01 dataset reach 70.55% and 63.89%, respectively. The Rank-1 and mAP in the visible-to-infrared retrieval mode of the RegDB dataset reach 91.80% and 82.08%, respectively. The effectiveness of the proposed method is verified on the public datasets.

张阔, 范馨月, 李嘉辉, 张干. 基于掩模重构与动态注意力的跨模态行人重识别[J]. 激光与光电子学进展, 2024, 61(10): 1015001. Kuo Zhang, Xinyue Fan, Jiahui Li, Gan Zhang. Cross-Modal Person Re-Identification Based on Mask Reconstruction with Dynamic Attention[J]. Laser & Optoelectronics Progress, 2024, 61(10): 1015001.

本文已被 1 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!