{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:43:53Z","timestamp":1784821433159,"version":"3.55.0"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197802","type":"print"},{"value":"9783031197819","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19781-9_28","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:12:59Z","timestamp":1666440779000},"page":"480-496","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":93,"title":["Cross-Modality Transformer for\u00a0Visible-Infrared Person Re-Identification"],"prefix":"10.1007","author":[{"given":"Kongzhu","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingqiao","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"28_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wan, L., Li, Z., Jing, Q., Sun, Z.: Neural feature search for rgb-infrared person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 587\u2013597 (2021)","DOI":"10.1109\/CVPR46437.2021.00065"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Choi, S., Lee, S., Kim, Y., Kim, T., Kim, C.: Hi-cmd: Hierarchical cross-modality disentanglement for visible-infrared person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10257\u201310266 (2020)","DOI":"10.1109\/CVPR42600.2020.01027"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Dai, P., Ji, R., Wang, H., Wu, Q., Huang, Y.: Cross-modality person re-identification with generative adversarial training. In: International Joint Conference on Artificial Intelligence, vol. 1, p. 2 (2018)","DOI":"10.24963\/ijcai.2018\/94"},{"key":"28_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"28_CR6","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1109\/TIP.2019.2928126","volume":"29","author":"Z Feng","year":"2019","unstructured":"Feng, Z., Lai, J., Xie, X.: Learning modality-specific representations for visible-infrared person re-identification. IEEE Trans. Image Process. 29, 579\u2013590 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Fu, C., Hu, Y., Wu, X., Shi, H., Mei, T., He, R.: Cm-nas: Cross-modality neural architecture search for visible-infrared person re-identification. arXiv preprint arXiv:2101.08467 (2021)","DOI":"10.1109\/ICCV48922.2021.01161"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Hao, X., Zhao, S., Ye, M., Shen, J.: Cross-modality person re-identification via modality confusion and center aggregation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 16403\u201316412 (2021)","DOI":"10.1109\/ICCV48922.2021.01609"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Hao, Y., Wang, N., Li, J., Gao, X.: Hsme: hypersphere manifold embedding for visible thermal person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8385\u20138392 (2019)","DOI":"10.1609\/aaai.v33i01.33018385"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W.: Transreid: Transformer-based object re-identification. arXiv preprint arXiv:2102.04378 (2021)","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"28_CR13","doi-asserted-by":"publisher","first-page":"8549","DOI":"10.1109\/TIP.2020.3016869","volume":"29","author":"K Jiang","year":"2020","unstructured":"Jiang, K., Zhang, T., Zhang, Y., Wu, F., Rui, Y.: Self-supervised agent learning for unsupervised cross-domain person re-identification. IEEE Trans. Image Process. 29, 8549\u20138560 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Kniaz, V.V., Knyaz, V.A., Hladuvka, J., Kropatsch, W.G., Mizginov, V.: Thermalgan: Multimodal color-to-thermal image translation for person re-identification in multispectral dataset. In: Proceedings of the European Conference on Computer Vision Workshops (2018)","DOI":"10.1007\/978-3-030-11024-6_46"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Li, D., Wei, X., Hong, X., Gong, Y.: Infrared-visible cross-modal person re-identification with an x modality. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 4610\u20134617 (2020)","DOI":"10.1609\/aaai.v34i04.5891"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Li, W., Zhu, X., Gong, S.: Harmonious attention network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2285\u20132294 (2018)","DOI":"10.1109\/CVPR.2018.00243"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., He, J., Zhang, T., Liu, X., Zhang, Y., Wu, F.: Diverse part discovery: Occluded person re-identification with part-aware transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2898\u20132907 (2021)","DOI":"10.1109\/CVPR46437.2021.00292"},{"key":"28_CR18","doi-asserted-by":"publisher","first-page":"4414","DOI":"10.1109\/TMM.2020.3042080","volume":"23","author":"H Liu","year":"2020","unstructured":"Liu, H., Tan, X., Zhou, X.: Parameter sharing exploration and hetero-center triplet loss for visible-thermal person re-identification. IEEE Trans. Multimedia 23, 4414\u20134425 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Cross-modality person re-identification with shared-specific feature transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 13379\u201313389 (2020)","DOI":"10.1109\/CVPR42600.2020.01339"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00190"},{"issue":"11","key":"28_CR22","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(11), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR23","doi-asserted-by":"publisher","first-page":"605","DOI":"10.3390\/s17030605","volume":"17","author":"DT Nguyen","year":"2017","unstructured":"Nguyen, D.T., Hong, H.G., Kim, K.W., Park, K.R.: Person recognition system based on a combination of body images from visible light and thermal cameras. Sensors 17, 605 (2017)","journal-title":"Sensors"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Oh Song, H., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4004\u20134012 (2016)","DOI":"10.1109\/CVPR.2016.434"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Park, H., Lee, S., Lee, J., Ham, B.: Learning by aligning: Visible-infrared person re-identification using cross-modal correspondences. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 12046\u201312055 (2021)","DOI":"10.1109\/ICCV48922.2021.01183"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In: Proceedings of the European Conference on Computer Vision, pp. 480\u2013496 (2018)","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"28_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Wang, G.A., et al.: Cross-modality paired-images generation for rgb-infrared person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12144\u201312151 (2020)","DOI":"10.1609\/aaai.v34i07.6894"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Wang, G., Zhang, T., Cheng, J., Liu, S., Yang, Y., Hou, Z.: Rgb-infrared cross-modality person re-identification via joint pixel and feature alignment. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3623\u20133632 (2019)","DOI":"10.1109\/ICCV.2019.00372"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Wang, G., Yuan, Y., Chen, X., Li, J., Zhou, X.: Learning discriminative features with multiple granularities for person re-identification. In: Proceedings of the ACM International Conference on Multimedia, pp. 274\u2013282 (2018)","DOI":"10.1145\/3240508.3240552"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, Z., Zheng, Y., Chuang, Y.Y., Satoh, S.: Learning to reduce dual-level discrepancy for infrared-visible person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 618\u2013626 (2019)","DOI":"10.1109\/CVPR.2019.00071"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Wei, Z., Yang, X., Wang, N., Gao, X.: Syncretic modality collaborative learning for visible infrared person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 225\u2013234 (2021)","DOI":"10.1109\/ICCV48922.2021.00029"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Wu, A., Zheng, W.S., Yu, H.X., Gong, S., Lai, J.: Rgb-infrared cross-modality person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5380\u20135389 (2017)","DOI":"10.1109\/ICCV.2017.575"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Wu, Q., et al.: Discover cross-modality nuances for visible-infrared person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4330\u20134339 (2021)","DOI":"10.1109\/CVPR46437.2021.00431"},{"issue":"10","key":"28_CR36","doi-asserted-by":"publisher","first-page":"2987","DOI":"10.1109\/TNNLS.2018.2861991","volume":"30","author":"X Yang","year":"2018","unstructured":"Yang, X., Zhou, P., Wang, M.: Person reidentification via structural deep metric learning. IEEE Trans. Neural Netw. Learn. Syst. 30(10), 2987\u20132998 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"28_CR37","doi-asserted-by":"publisher","first-page":"9387","DOI":"10.1109\/TIP.2020.2998275","volume":"29","author":"M Ye","year":"2020","unstructured":"Ye, M., Lan, X., Leng, Q., Shen, J.: Cross-modality person re-identification via modality-aware collaborative ensemble learning. IEEE Trans. Image Process. 29, 9387\u20139399 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Ye, M., Lan, X., Li, J., Yuen, P.: Hierarchical discriminative learning for visible thermal person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12293"},{"key":"28_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/978-3-030-58520-4_14","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Ye","year":"2020","unstructured":"Ye, M., Shen, J., J. Crandall, D., Shao, L., Luo, J.: Dynamic dual-attentive aggregation learning for visible-infrared person re-identification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 229\u2013247. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_14"},{"key":"28_CR40","doi-asserted-by":"publisher","first-page":"2872","DOI":"10.1109\/TPAMI.2021.3054775","volume":"44","author":"M Ye","year":"2021","unstructured":"Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., Hoi, S.C.: Deep learning for person re-identification: A survey and outlook. IEEE Trans. Pattern Anal. Mach. Intell. 44, 2872\u20132893 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Ye, M., Wang, Z., Lan, X., Yuen, P.C.: Visible thermal person re-identification via dual-constrained top-ranking. In: International Joint Conference on Artificial Intelligence, vol. 1, p. 2 (2018)","DOI":"10.24963\/ijcai.2018\/152"},{"key":"28_CR42","unstructured":"Zheng, L., Yang, Y., Hauptmann, A.G.: Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984 (2016)"},{"issue":"3","key":"28_CR43","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1109\/TPAMI.2012.138","volume":"35","author":"WS Zheng","year":"2012","unstructured":"Zheng, W.S., Gong, S., Xiang, T.: Reidentification by relative distance comparison. IEEE Trans. Pattern Anal. Mach. Intell. 35(3), 653\u2013668 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"28_CR44","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1318\u20131327 (2017)","DOI":"10.1109\/CVPR.2017.389"},{"key":"28_CR45","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19781-9_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:40:55Z","timestamp":1710261655000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19781-9_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197802","9783031197819"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19781-9_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}