Multi-scale feature correspondence and restriction mechanism for visible X-ray baggage re-Identification
文献类型：期刊论文
| 作者 | Chan, Sixian1,2,3; Cui, Jiaao2; Wu, Yonggan1,3; Wang, Hongqiang1,3 ; Bai, Cong2
|
| 刊名 | MULTIMEDIA SYSTEMS
 |
| 出版日期 | 2024-12-01 |
| 卷号 | 30 |
| 关键词 | Cross-modality Re-Identification Security inspection |
| ISSN号 | 0942-4962 |
| DOI | 10.1007/s00530-024-01513-7 |
| 通讯作者 | Wang, Hongqiang(hqwang126@126.com) |
| 英文摘要 | Recently, social security surveillance has posed a new AI challenge, i.e., Visible-X-ray baggage Re-Identification (VX-ReID), which aims to re-identify and retrieve baggage between visible and X-ray imaging modalities. Compared with cross-modality person re-identification, VX-ReID has two distinctive bottlenecks: shape deformation and feature entanglement. For the former, the shape of the baggage can change largely, resulting in serious feature unrobustness. For the latter, the X-ray images often contain the contents of the baggage, which are not visible in daylight images. These will greatly affect the performance of representational learning loss functions (like ID Loss) in the Re-ID task. In this paper, we propose a cross-modality multi-scale feature correspondence model (CMMFC) for VX-ReID. Specifically, we devise and calculate multiple feature correspondences between modalities on multiple-scale feature maps endowed to overcome the deformation problem. We also utilize a novel feature restriction mechanism (FRM) to alleviate the feature entanglement problem, which imposes different constraints on features at different scales and accurately drives networks to distinctive modality-irrelevant features. Finally, CMMFC is extensively evaluated on our dataset RX01. Experiments show that our proposed method achieves state-of-the-art performance on dataset RX01. |
| 资助项目 | Zhejiang Provincial Natural Science Foundation of China ; Anhui key Laboratory of Bionic Sensing and AdvancedRobot Technology Project[AHFS2024KF04] ; National Natural Science Foundation of China[U20A20196] ; National Natural Science Foundation of China[61906168] ; [LY23F020023] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001331229600001 |
| 出版者 | SPRINGER |
| 资助机构 | Zhejiang Provincial Natural Science Foundation of China ; Anhui key Laboratory of Bionic Sensing and AdvancedRobot Technology Project ; National Natural Science Foundation of China |
| 源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/134551]  |
| 专题 | 中国科学院合肥物质科学研究院 |
| 通讯作者 | Wang, Hongqiang |
| 作者单位 | 1.Chinese Acad Sci, Hefei Inst Phys Sci, Anhui Key Lab Bion Sensing & Adv Robot Technol, Hefei 230031, Anhui, Peoples R China 2.Zhejiang Univ Technol, Coll Comp Sci & Technol, Hangzhou 310023, Zhejiang, Peoples R China 3.Anhui QixinMingzhi Technol Co Ltd, Hefei 230071, Anhui, Peoples R China |
| 推荐引用方式 GB/T 7714 | Chan, Sixian,Cui, Jiaao,Wu, Yonggan,et al. Multi-scale feature correspondence and restriction mechanism for visible X-ray baggage re-Identification[J]. MULTIMEDIA SYSTEMS,2024,30. |
| APA | Chan, Sixian,Cui, Jiaao,Wu, Yonggan,Wang, Hongqiang,&Bai, Cong.(2024).Multi-scale feature correspondence and restriction mechanism for visible X-ray baggage re-Identification.MULTIMEDIA SYSTEMS,30. |
| MLA | Chan, Sixian,et al."Multi-scale feature correspondence and restriction mechanism for visible X-ray baggage re-Identification".MULTIMEDIA SYSTEMS 30(2024). |
入库方式： OAI收割
来源：合肥物质科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。