AMC-Net: Attentive modality-consistent network for visible-infrared person re-identification
Visible-infrared person re-identification (VI-ReID) aims at matching people across images from RGB and infrared modality. Existing methods tend to utilize the readily available models to extract features, ignoring mining spatial and channel information of features. In this paper, we propose an atten...
Saved in:
Published in | Neurocomputing (Amsterdam) Vol. 463; pp. 226 - 236 |
---|---|
Main Authors | , , , , , |
Format | Journal Article |
Language | English |
Published |
Elsevier B.V
06.11.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Visible-infrared person re-identification (VI-ReID) aims at matching people across images from RGB and infrared modality. Existing methods tend to utilize the readily available models to extract features, ignoring mining spatial and channel information of features. In this paper, we propose an attentive modality-consistent network (AMC-Net) for VI-ReID. Firstly, to avoid the damage to discriminability of features caused by overfitting of local regions in the network, a context-aware attention block (CAB) is designed to mine the spatial information of the whole person region by magnifying the perception scope of convolution layers. Secondly, the attentive channel aggregation block (ACB) is adopted to mine the channel information with richer semantic cues by considering local cross-channel interactive information. Thirdly, we propose a modality-consistent regularizer to narrow down the discrepancy of high order features between heterogeneous images. Extensive experiments on two datasets indicate that the proposed method outperforms the state-of-the-art methods. |
---|---|
AbstractList | Visible-infrared person re-identification (VI-ReID) aims at matching people across images from RGB and infrared modality. Existing methods tend to utilize the readily available models to extract features, ignoring mining spatial and channel information of features. In this paper, we propose an attentive modality-consistent network (AMC-Net) for VI-ReID. Firstly, to avoid the damage to discriminability of features caused by overfitting of local regions in the network, a context-aware attention block (CAB) is designed to mine the spatial information of the whole person region by magnifying the perception scope of convolution layers. Secondly, the attentive channel aggregation block (ACB) is adopted to mine the channel information with richer semantic cues by considering local cross-channel interactive information. Thirdly, we propose a modality-consistent regularizer to narrow down the discrepancy of high order features between heterogeneous images. Extensive experiments on two datasets indicate that the proposed method outperforms the state-of-the-art methods. |
Author | Yao, Rui Wang, Hanzheng Zhou, Yong Chen, Silin Zhao, Jiaqi Chen, Ying |
Author_xml | – sequence: 1 givenname: Hanzheng surname: Wang fullname: Wang, Hanzheng organization: School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China – sequence: 2 givenname: Jiaqi surname: Zhao fullname: Zhao, Jiaqi email: jiaqizhao@cumt.edu.cn organization: School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China – sequence: 3 givenname: Yong surname: Zhou fullname: Zhou, Yong organization: School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China – sequence: 4 givenname: Rui surname: Yao fullname: Yao, Rui organization: School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China – sequence: 5 givenname: Ying surname: Chen fullname: Chen, Ying organization: School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China – sequence: 6 givenname: Silin surname: Chen fullname: Chen, Silin organization: School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China |
BookMark | eNp9kMFKAzEURYNUsK3-gYv5gYwvGWcm40IoRatQdaM7IWSSF0htk5LESv_eGera1YUL93A5MzLxwSMh1wxKBqy52ZQev3XYlRw4K0GUUFdnZMpEy6ngopmQKXS8prxi_ILMUtoAsJbxbko-Fy9L-or5rljkjD67Axa7YNTW5SPVwSeXxrrwmH9C_CpsiMXBJddvkTpvo4poij3GFHwRh8qMDOu0yi74S3Ju1Tbh1V_Oycfjw_vyia7fVs_LxZrqCppMa1EzzlnNmG1ri7UAAcpWuue6qXoLre1sq3rVKANtK4zolKi63hgBVgnVVHNye-LqGFKKaOU-up2KR8lAjobkRp4MydGQBCEHQ8Ps_jTD4dvBYZRJO_QajYuoszTB_Q_4BVPCdQM |
CitedBy_id | crossref_primary_10_1016_j_neucom_2022_12_042 crossref_primary_10_3390_s23031504 crossref_primary_10_1007_s00371_023_02923_w crossref_primary_10_1016_j_engappai_2023_105919 crossref_primary_10_1109_ACCESS_2023_3297891 crossref_primary_10_1016_j_neucom_2022_04_081 crossref_primary_10_1145_3573203 crossref_primary_10_3390_electronics11030454 crossref_primary_10_1145_3674737 crossref_primary_10_1016_j_neucom_2023_127110 crossref_primary_10_1109_TCSVT_2023_3287300 |
Cites_doi | 10.1609/aaai.v34i04.5891 10.1109/TIFS.2019.2921454 10.1109/TPAMI.2017.2709749 10.1016/j.neucom.2020.12.018 10.1007/978-3-319-46484-8_48 10.3390/s17030605 10.1109/TIFS.2020.3001665 10.1609/aaai.v32i1.12293 10.1109/TMM.2016.2605058 10.24963/ijcai.2018/94 10.1016/j.neucom.2019.12.100 10.1109/TIP.2020.2973812 10.1016/j.neucom.2020.10.019 10.1007/978-3-319-10605-2_22 |
ContentType | Journal Article |
Copyright | 2021 Elsevier B.V. |
Copyright_xml | – notice: 2021 Elsevier B.V. |
DBID | AAYXX CITATION |
DOI | 10.1016/j.neucom.2021.08.053 |
DatabaseName | CrossRef |
DatabaseTitle | CrossRef |
DatabaseTitleList | |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISSN | 1872-8286 |
EndPage | 236 |
ExternalDocumentID | 10_1016_j_neucom_2021_08_053 S0925231221012376 |
GroupedDBID | --- --K --M .DC .~1 0R~ 123 1B1 1~. 1~5 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXLA AAXUO AAYFN ABBOA ABCQJ ABFNM ABJNI ABMAC ABYKQ ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE AEBSH AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W KOM LG9 M41 MO0 MOBAO N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SPC SPCBC SSN SSV SSZ T5K ZMT ~G- 29N AAQXK AAXKI AAYXX ABXDB ACNNM ADJOM ADMUD AFJKZ AKRWK ASPBG AVWKF AZFZN CITATION EJD FEDTE FGOYB HLZ HVGLF HZ~ R2- RIG SBC SEW WUQ XPP |
ID | FETCH-LOGICAL-c306t-5851221511f75fe58080af3cb2c63bf07f9f7aba6ad0778d89a839bdd80fa8a63 |
IEDL.DBID | AIKHN |
ISSN | 0925-2312 |
IngestDate | Thu Sep 26 16:07:44 EDT 2024 Fri Feb 23 02:41:49 EST 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | Deep learning Attention mechanism Cross-modality person re-identification Image retrieval |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c306t-5851221511f75fe58080af3cb2c63bf07f9f7aba6ad0778d89a839bdd80fa8a63 |
PageCount | 11 |
ParticipantIDs | crossref_primary_10_1016_j_neucom_2021_08_053 elsevier_sciencedirect_doi_10_1016_j_neucom_2021_08_053 |
PublicationCentury | 2000 |
PublicationDate | 2021-11-06 |
PublicationDateYYYYMMDD | 2021-11-06 |
PublicationDate_xml | – month: 11 year: 2021 text: 2021-11-06 day: 06 |
PublicationDecade | 2020 |
PublicationTitle | Neurocomputing (Amsterdam) |
PublicationYear | 2021 |
Publisher | Elsevier B.V |
Publisher_xml | – name: Elsevier B.V |
References | Wang, Girshick, Gupta, He (b0085) 2018 Ioffe, Szegedy (b0140) 2015 Luo (b0070) 2020 J. Xie, Z. Ma, J. Lei, G. Zhang, J.-H. Xue, Z.-H. Tan, J. Guo, Advanced dropout: A model-free methodology for bayesian dropout optimization, IEEE Transactions on Pattern Analysis and Machine Intelligence. Chen, Ding, Xie, Yuan, Chen, Yang, Ren, Wang (b0090) 2019 A. Das, A. Chakraborty, A.K. Roy-Chowdhury, Consistent re-identification in a camera network, in: European Conference on Computer Vision, Springer, 2014, pp. 330–345. L.-C. Chen, G. Papandreou, F. Schroff, H. Adam, Rethinking atrous convolution for semantic image segmentation, arXiv preprint arXiv:1706.05587. Liu, Xiao, Fan, Zeng, Zhang, Jiang (b0030) 2021; 423 Zheng, Shen, Tian, Wang, Wang, Tian (b0190) 2015 Woo, Park, Lee, Kweon (b0195) 2018 Zheng, Yang, Tian (b0005) 2017; 40 Fang, Zhou, Roy, Petersson, Harandi (b0120) 2019 Ye, Liang, Yu, Wang, Leng, Xiao, Chen, Hu (b0010) 2016; 18 Ye, Lan, Leng (b0130) 2019 P.Z.P.L.W.Z. Qilong Wang, Banggu Wu, Q. Hu, Eca-net: Efficient channel attention for deep convolutional neural networks, in: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. He, Zhang, Ren, Sun (b0105) 2016 H. Liu, X. Tan, X. Zhou, Parameter sharing exploration and hetero-center triplet loss for visible-thermal person re-identification, IEEE Transactions on Multimedia. Chu, Yang, Ouyang, Ma, Yuille, Wang (b0150) 2017 Yu, Wang, Chen, Wei (b0155) 2014 Li, Yin, Liu, Yang, Wang (b0025) 2021; 433 Wang, Wang, Zheng, Chuang, Satoh (b0065) 2019 Zhu, Yang, Wang, Zhao, Hu, Tao (b0075) 2020; 386 Wang, Chen, Wu, Wang (b0055) 2018 Z. Ma, Y. Lai, J. Xie, D. Meng, W.B. Kleijn, J. Guo, J. Yu, Dirichlet process mixture of generalized inverted dirichlet distributions for positive vector data with extended variational inference, IEEE Transactions on Neural Networks and Learning Systems. Chang, Ding, Xie, Bhunia, Li, Ma, Wu, Guo, Song (b0110) 2020; 29 M. Ye, J. Shen, G. Lin, T. Xiang, L. Shao, S.C. Hoi, Deep learning for person re-identification: A survey and outlook, IEEE Transactions on Pattern Analysis and Machine Intelligence. D. Li, X. Wei, X. Hong, Y. Gong, Infrared-visible cross-modal person re-identification with an x modality, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, 2020, pp. 4610–4617. Zhang, Lan, Zeng, Jin, Chen (b0125) 2020 Chattopadhay, Sarkar, Howlader, Balasubramanian (b0215) 2018 Zheng, Zhang, Sun, Chandraker, Yang, Tian (b0045) 2017 Nguyen, Hong, Kim, Park (b0185) 2017; 17 Luo, Gu, Liao, Lai, Jiang (b0135) 2019 Xu, Zhao, Zhu, Wang, Ouyang (b0115) 2018 M. Ye, X. Lan, J. Li, P. Yuen, Hierarchical discriminative learning for visible thermal person re-identification, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, 2018. Hu, Shen, Sun (b0200) 2018 Liao, Hu, Zhu, Li (b0015) 2015 Ye, Shen, Shao (b0210) 2020; 16 R.R. Varior, M. Haloi, G. Wang, Gated siamese convolutional neural network architecture for human re-identification, in: European Conference on Computer Vision, Springer, 2016, pp. 791–808. Ye, Lan, Wang, Yuen (b0060) 2019; 15 Chen, Badrinarayanan, Lee, Rabinovich (b0165) 2018 L. Zheng, Y. Yang, A.G. Hauptmann, Person re-identification: Past, present and future, arXiv preprint arXiv:1610.02984. Wu, Zheng, Yu, Gong, Lai (b0035) 2017 P. Dai, R. Ji, H. Wang, Q. Wu, Y. Huang, Cross-modality person re-identification with generative adversarial training., in: IJCAI, vol. 1, 2018, p. 2. Zheng (10.1016/j.neucom.2021.08.053_b0190) 2015 Chen (10.1016/j.neucom.2021.08.053_b0090) 2019 10.1016/j.neucom.2021.08.053_b0175 Zhu (10.1016/j.neucom.2021.08.053_b0075) 2020; 386 Woo (10.1016/j.neucom.2021.08.053_b0195) 2018 Ye (10.1016/j.neucom.2021.08.053_b0010) 2016; 18 Ye (10.1016/j.neucom.2021.08.053_b0210) 2020; 16 Ye (10.1016/j.neucom.2021.08.053_b0060) 2019; 15 Wang (10.1016/j.neucom.2021.08.053_b0055) 2018 Wang (10.1016/j.neucom.2021.08.053_b0065) 2019 Xu (10.1016/j.neucom.2021.08.053_b0115) 2018 Fang (10.1016/j.neucom.2021.08.053_b0120) 2019 Ioffe (10.1016/j.neucom.2021.08.053_b0140) 2015 10.1016/j.neucom.2021.08.053_b0170 Wang (10.1016/j.neucom.2021.08.053_b0085) 2018 Yu (10.1016/j.neucom.2021.08.053_b0155) 2014 10.1016/j.neucom.2021.08.053_b0050 10.1016/j.neucom.2021.08.053_b0095 10.1016/j.neucom.2021.08.053_b0100 Luo (10.1016/j.neucom.2021.08.053_b0135) 2019 Wu (10.1016/j.neucom.2021.08.053_b0035) 2017 10.1016/j.neucom.2021.08.053_b0145 Chu (10.1016/j.neucom.2021.08.053_b0150) 2017 Nguyen (10.1016/j.neucom.2021.08.053_b0185) 2017; 17 Hu (10.1016/j.neucom.2021.08.053_b0200) 2018 Chattopadhay (10.1016/j.neucom.2021.08.053_b0215) 2018 Zheng (10.1016/j.neucom.2021.08.053_b0005) 2017; 40 Zheng (10.1016/j.neucom.2021.08.053_b0045) 2017 10.1016/j.neucom.2021.08.053_b0205 Luo (10.1016/j.neucom.2021.08.053_b0070) 2020 Li (10.1016/j.neucom.2021.08.053_b0025) 2021; 433 He (10.1016/j.neucom.2021.08.053_b0105) 2016 Zhang (10.1016/j.neucom.2021.08.053_b0125) 2020 Liao (10.1016/j.neucom.2021.08.053_b0015) 2015 10.1016/j.neucom.2021.08.053_b0180 Chen (10.1016/j.neucom.2021.08.053_b0165) 2018 10.1016/j.neucom.2021.08.053_b0080 Chang (10.1016/j.neucom.2021.08.053_b0110) 2020; 29 Ye (10.1016/j.neucom.2021.08.053_b0130) 2019 10.1016/j.neucom.2021.08.053_b0020 Liu (10.1016/j.neucom.2021.08.053_b0030) 2021; 423 10.1016/j.neucom.2021.08.053_b0160 10.1016/j.neucom.2021.08.053_b0040 |
References_xml | – start-page: 794 year: 2018 end-page: 803 ident: b0165 article-title: Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks publication-title: International Conference on Machine Learning, PMLR contributor: fullname: Rabinovich – year: 2019 ident: b0135 article-title: Bag of tricks and a strong baseline for deep person re-identification publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops contributor: fullname: Jiang – volume: 433 start-page: 10 year: 2021 end-page: 18 ident: b0025 article-title: Triplet online instance matching loss for person re-identification publication-title: Neurocomputing contributor: fullname: Wang – volume: 15 start-page: 407 year: 2019 end-page: 419 ident: b0060 article-title: Bi-directional center-constrained top-ranking for visible thermal person re-identification publication-title: IEEE Transactions on Information Forensics and Security contributor: fullname: Yuen – start-page: 8351 year: 2019 end-page: 8361 ident: b0090 article-title: Abd-net: Attentive but diverse person re-identification publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision contributor: fullname: Wang – start-page: 1116 year: 2015 end-page: 1124 ident: b0190 article-title: Scalable person re-identification: A benchmark publication-title: Proceedings of the IEEE International Conference on Computer Vision contributor: fullname: Tian – volume: 29 start-page: 4683 year: 2020 end-page: 4695 ident: b0110 article-title: The devil is in the channels: Mutual-channel loss for fine-grained image classification publication-title: IEEE Transactions on Image Processing contributor: fullname: Song – year: 2020 ident: b0070 article-title: Dynamic dual-attentive aggregation learning for visible-infrared person re-identification publication-title: Proceedings of the European Conference on Computer Vision (ECCV) contributor: fullname: Luo – start-page: 1470 year: 2018 end-page: 1478 ident: b0055 article-title: Person re-identification with cascaded pairwise convolutions publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition contributor: fullname: Wang – start-page: 8030 year: 2019 end-page: 8039 ident: b0120 article-title: Bilinear attention networks for person retrieval publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision contributor: fullname: Harandi – start-page: 2197 year: 2015 end-page: 2206 ident: b0015 article-title: Person re-identification by local maximal occurrence representation and metric learning publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition contributor: fullname: Li – start-page: 618 year: 2019 end-page: 626 ident: b0065 article-title: Learning to reduce dual-level discrepancy for infrared-visible person re-identification publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition contributor: fullname: Satoh – start-page: 3 year: 2018 end-page: 19 ident: b0195 article-title: Cbam: Convolutional block attention module publication-title: Proceedings of the European Conference on Computer Vision (ECCV) contributor: fullname: Kweon – start-page: 770 year: 2016 end-page: 778 ident: b0105 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition contributor: fullname: Sun – start-page: 1831 year: 2017 end-page: 1840 ident: b0150 article-title: Multi-context attention for human pose estimation publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition contributor: fullname: Wang – volume: 17 start-page: 605 year: 2017 ident: b0185 article-title: Person recognition system based on a combination of body images from visible light and thermal cameras publication-title: Sensors contributor: fullname: Park – start-page: 839 year: 2018 end-page: 847 ident: b0215 article-title: Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks publication-title: in: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE contributor: fullname: Balasubramanian – start-page: 1367 year: 2017 end-page: 1376 ident: b0045 article-title: Person re-identification in the wild publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition contributor: fullname: Tian – start-page: 3186 year: 2020 end-page: 3195 ident: b0125 article-title: Relation-aware global attention for person re-identification publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition contributor: fullname: Chen – start-page: 448 year: 2015 end-page: 456 ident: b0140 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: International Conference on Machine Learning, PMLR contributor: fullname: Szegedy – volume: 40 start-page: 1224 year: 2017 end-page: 1244 ident: b0005 article-title: Sift meets cnn: A decade survey of instance retrieval publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence contributor: fullname: Tian – volume: 386 start-page: 97 year: 2020 end-page: 109 ident: b0075 article-title: Hetero-center loss for cross-modality person re-identification publication-title: Neurocomputing contributor: fullname: Tao – volume: 16 start-page: 728 year: 2020 end-page: 739 ident: b0210 article-title: Visible-infrared person re-identification via homogeneous augmented tri-modal learning publication-title: IEEE Transactions on Information Forensics and Security contributor: fullname: Shao – start-page: 5380 year: 2017 end-page: 5389 ident: b0035 article-title: Rgb-infrared cross-modality person re-identification publication-title: Proceedings of the IEEE International Conference on Computer Vision contributor: fullname: Lai – volume: 18 start-page: 2553 year: 2016 end-page: 2566 ident: b0010 article-title: Person reidentification via ranking aggregation of similarity pulling and dissimilarity pushing publication-title: IEEE Transactions on Multimedia contributor: fullname: Hu – start-page: 364 year: 2014 end-page: 375 ident: b0155 article-title: Mixed pooling for convolutional neural networks publication-title: International Conference on Rough Sets and Knowledge Technology, Springer contributor: fullname: Wei – start-page: 2119 year: 2018 end-page: 2128 ident: b0115 article-title: Attention-aware compositional network for person re-identification publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition contributor: fullname: Ouyang – start-page: 347 year: 2019 end-page: 355 ident: b0130 article-title: Modality-aware collaborative learning for visible thermal person re-identification publication-title: Proceedings of the 27th ACM International Conference on Multimedia contributor: fullname: Leng – start-page: 7132 year: 2018 end-page: 7141 ident: b0200 article-title: Squeeze-and-excitation networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition contributor: fullname: Sun – volume: 423 start-page: 57 year: 2021 end-page: 70 ident: b0030 article-title: Prgcn: Probability prediction with graph convolutional network for person re-identification publication-title: Neurocomputing contributor: fullname: Jiang – start-page: 7794 year: 2018 end-page: 7803 ident: b0085 article-title: Non-local neural networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition contributor: fullname: He – ident: 10.1016/j.neucom.2021.08.053_b0100 doi: 10.1609/aaai.v34i04.5891 – start-page: 347 year: 2019 ident: 10.1016/j.neucom.2021.08.053_b0130 article-title: Modality-aware collaborative learning for visible thermal person re-identification contributor: fullname: Ye – start-page: 770 year: 2016 ident: 10.1016/j.neucom.2021.08.053_b0105 article-title: Deep residual learning for image recognition contributor: fullname: He – start-page: 794 year: 2018 ident: 10.1016/j.neucom.2021.08.053_b0165 article-title: Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks contributor: fullname: Chen – volume: 15 start-page: 407 year: 2019 ident: 10.1016/j.neucom.2021.08.053_b0060 article-title: Bi-directional center-constrained top-ranking for visible thermal person re-identification publication-title: IEEE Transactions on Information Forensics and Security doi: 10.1109/TIFS.2019.2921454 contributor: fullname: Ye – ident: 10.1016/j.neucom.2021.08.053_b0205 – start-page: 364 year: 2014 ident: 10.1016/j.neucom.2021.08.053_b0155 article-title: Mixed pooling for convolutional neural networks contributor: fullname: Yu – ident: 10.1016/j.neucom.2021.08.053_b0160 – volume: 40 start-page: 1224 issue: 5 year: 2017 ident: 10.1016/j.neucom.2021.08.053_b0005 article-title: Sift meets cnn: A decade survey of instance retrieval publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2017.2709749 contributor: fullname: Zheng – start-page: 2119 year: 2018 ident: 10.1016/j.neucom.2021.08.053_b0115 article-title: Attention-aware compositional network for person re-identification contributor: fullname: Xu – start-page: 1470 year: 2018 ident: 10.1016/j.neucom.2021.08.053_b0055 article-title: Person re-identification with cascaded pairwise convolutions contributor: fullname: Wang – start-page: 7794 year: 2018 ident: 10.1016/j.neucom.2021.08.053_b0085 article-title: Non-local neural networks contributor: fullname: Wang – year: 2019 ident: 10.1016/j.neucom.2021.08.053_b0135 article-title: Bag of tricks and a strong baseline for deep person re-identification contributor: fullname: Luo – volume: 433 start-page: 10 year: 2021 ident: 10.1016/j.neucom.2021.08.053_b0025 article-title: Triplet online instance matching loss for person re-identification publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.12.018 contributor: fullname: Li – ident: 10.1016/j.neucom.2021.08.053_b0050 doi: 10.1007/978-3-319-46484-8_48 – ident: 10.1016/j.neucom.2021.08.053_b0080 – ident: 10.1016/j.neucom.2021.08.053_b0170 – volume: 17 start-page: 605 issue: 3 year: 2017 ident: 10.1016/j.neucom.2021.08.053_b0185 article-title: Person recognition system based on a combination of body images from visible light and thermal cameras publication-title: Sensors doi: 10.3390/s17030605 contributor: fullname: Nguyen – volume: 16 start-page: 728 year: 2020 ident: 10.1016/j.neucom.2021.08.053_b0210 article-title: Visible-infrared person re-identification via homogeneous augmented tri-modal learning publication-title: IEEE Transactions on Information Forensics and Security doi: 10.1109/TIFS.2020.3001665 contributor: fullname: Ye – start-page: 8030 year: 2019 ident: 10.1016/j.neucom.2021.08.053_b0120 article-title: Bilinear attention networks for person retrieval contributor: fullname: Fang – start-page: 1831 year: 2017 ident: 10.1016/j.neucom.2021.08.053_b0150 article-title: Multi-context attention for human pose estimation contributor: fullname: Chu – ident: 10.1016/j.neucom.2021.08.053_b0040 doi: 10.1609/aaai.v32i1.12293 – volume: 18 start-page: 2553 issue: 12 year: 2016 ident: 10.1016/j.neucom.2021.08.053_b0010 article-title: Person reidentification via ranking aggregation of similarity pulling and dissimilarity pushing publication-title: IEEE Transactions on Multimedia doi: 10.1109/TMM.2016.2605058 contributor: fullname: Ye – start-page: 5380 year: 2017 ident: 10.1016/j.neucom.2021.08.053_b0035 article-title: Rgb-infrared cross-modality person re-identification contributor: fullname: Wu – start-page: 7132 year: 2018 ident: 10.1016/j.neucom.2021.08.053_b0200 article-title: Squeeze-and-excitation networks contributor: fullname: Hu – start-page: 1367 year: 2017 ident: 10.1016/j.neucom.2021.08.053_b0045 article-title: Person re-identification in the wild contributor: fullname: Zheng – year: 2020 ident: 10.1016/j.neucom.2021.08.053_b0070 article-title: Dynamic dual-attentive aggregation learning for visible-infrared person re-identification contributor: fullname: Luo – start-page: 3186 year: 2020 ident: 10.1016/j.neucom.2021.08.053_b0125 article-title: Relation-aware global attention for person re-identification contributor: fullname: Zhang – start-page: 8351 year: 2019 ident: 10.1016/j.neucom.2021.08.053_b0090 article-title: Abd-net: Attentive but diverse person re-identification contributor: fullname: Chen – ident: 10.1016/j.neucom.2021.08.053_b0145 – start-page: 839 year: 2018 ident: 10.1016/j.neucom.2021.08.053_b0215 article-title: Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks contributor: fullname: Chattopadhay – ident: 10.1016/j.neucom.2021.08.053_b0180 – ident: 10.1016/j.neucom.2021.08.053_b0095 doi: 10.24963/ijcai.2018/94 – start-page: 2197 year: 2015 ident: 10.1016/j.neucom.2021.08.053_b0015 article-title: Person re-identification by local maximal occurrence representation and metric learning contributor: fullname: Liao – start-page: 448 year: 2015 ident: 10.1016/j.neucom.2021.08.053_b0140 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift contributor: fullname: Ioffe – start-page: 3 year: 2018 ident: 10.1016/j.neucom.2021.08.053_b0195 article-title: Cbam: Convolutional block attention module contributor: fullname: Woo – volume: 386 start-page: 97 year: 2020 ident: 10.1016/j.neucom.2021.08.053_b0075 article-title: Hetero-center loss for cross-modality person re-identification publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.12.100 contributor: fullname: Zhu – start-page: 1116 year: 2015 ident: 10.1016/j.neucom.2021.08.053_b0190 article-title: Scalable person re-identification: A benchmark contributor: fullname: Zheng – volume: 29 start-page: 4683 year: 2020 ident: 10.1016/j.neucom.2021.08.053_b0110 article-title: The devil is in the channels: Mutual-channel loss for fine-grained image classification publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2020.2973812 contributor: fullname: Chang – ident: 10.1016/j.neucom.2021.08.053_b0175 – volume: 423 start-page: 57 year: 2021 ident: 10.1016/j.neucom.2021.08.053_b0030 article-title: Prgcn: Probability prediction with graph convolutional network for person re-identification publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.10.019 contributor: fullname: Liu – start-page: 618 year: 2019 ident: 10.1016/j.neucom.2021.08.053_b0065 article-title: Learning to reduce dual-level discrepancy for infrared-visible person re-identification contributor: fullname: Wang – ident: 10.1016/j.neucom.2021.08.053_b0020 doi: 10.1007/978-3-319-10605-2_22 |
SSID | ssj0017129 |
Score | 2.4448068 |
Snippet | Visible-infrared person re-identification (VI-ReID) aims at matching people across images from RGB and infrared modality. Existing methods tend to utilize the... |
SourceID | crossref elsevier |
SourceType | Aggregation Database Publisher |
StartPage | 226 |
SubjectTerms | Attention mechanism Cross-modality person re-identification Deep learning Image retrieval |
Title | AMC-Net: Attentive modality-consistent network for visible-infrared person re-identification |
URI | https://dx.doi.org/10.1016/j.neucom.2021.08.053 |
Volume | 463 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEB76uHjxLdZHycFr7G62SXa9LUWpSnvRQg_CkmwSqOi21K1Hf7tJdlcUxIPHHQgsM8l8X8g3MwAXeRIHxr3q5pQLPAwlwTJiCsc0YYklc0z6orDJlI1nw7s5nbdg1NTCOFllnfurnO6zdW0Z1N4crBaLwUOQEHuLCglxLarsOWlD18LRcNiBbnp7P55-PSbwkFQt9wjFbkFTQedlXoXeONkIsVjne3nS6HeE-oY6N7uwXdNFlFZ_tActXezDTjOKAdUn8wCe0skIT3V5hdKydAKgd41el8qTbJw7EeybM6OiUn0jS1WRKyuXLxrbPbZ2MnS08uwbra1J1SIiH7dDmN1cP47GuB6cgHN7Ayixe-ojDstDw6nR1PWOFCbKJclZJE3ATWK4kIIJFXAeqzgRlidJpWzcRCxYdASdYlnoY0BcGwv4RFFhsV4aImQYSEmlkYzoUMU9wI2zslXVHyNrhGPPWeXczDk3c9MuadQD3ng0-xHnzKbwP1ee_HvlKWy5L19ByM6gU643-txSiVL2oX35EfbrDfMJwv3KCw |
link.rule.ids | 315,786,790,4521,24144,27955,27956,45618,45712 |
linkProvider | Elsevier |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV09T8MwELVKGWDhG1E-PbCaJk5tJ2xVRVWg7UIrdUCK7NiWQJBWJWXkt-NzEgQSYmC9xFJ0Z997kd_dIXSZJXFg4VY3Y0KSTqgoURHXJGYJTxyZ48oXhY3GfDDt3M3YrIF6dS0MyCqr3F_mdJ-tK0u78mZ78fTUfggS6v6iQkqhRZU7J2toHdgA6LquPr50HqEIadlwjzICr9f1c17klZsViEaoQzrfyZNFv-PTN8zp76Ctiizibvk9u6hh8j20XQ9iwNW53EeP3VGPjE1xjbtFAfKfd4Nf59pTbJKBBPYNzDgvNd_YEVUMReXqxRC3w5YgQscLz73x0pl0JSHyUTtA0_7NpDcg1dgEkjn-XxC46KOA5KEVzBoGnSOljTJFMx4pGwibWCGV5FIHQsQ6TqRjSUprFzUZSx4domY-z80RwsJYB_dUM-mQXlkqVRgoxZRVnJpQxy1Eameli7I7RlrLxp7T0rkpODeFWZcsaiFRezT9EeXUJfA_Vx7_e-UF2hhMRsN0eDu-P0Gb8MTXEvJT1CyWK3PmSEWhzv2m-QSNtsrg |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=AMC-Net%3A+Attentive+modality-consistent+network+for+visible-infrared+person+re-identification&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Wang%2C+Hanzheng&rft.au=Zhao%2C+Jiaqi&rft.au=Zhou%2C+Yong&rft.au=Yao%2C+Rui&rft.date=2021-11-06&rft.issn=0925-2312&rft.volume=463&rft.spage=226&rft.epage=236&rft_id=info:doi/10.1016%2Fj.neucom.2021.08.053&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neucom_2021_08_053 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon |