{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:20:49Z","timestamp":1740108049545,"version":"3.37.3"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"31","license":[{"start":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T00:00:00Z","timestamp":1693612800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T00:00:00Z","timestamp":1693612800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["61961040","61771089","U1903215"],"award-info":[{"award-number":["61961040","61771089","U1903215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Sichuan Provincial Key Research and Development Program","award":["2021YFQ0011"],"award-info":[{"award-number":["2021YFQ0011"]}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s00521-023-08913-2","type":"journal-article","created":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T13:01:37Z","timestamp":1693659697000},"page":"23213-23223","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Vision transformer with multiple granularities for person re-identification"],"prefix":"10.1007","volume":"35","author":[{"given":"Bingcai","family":"Chen","sequence":"first","affiliation":[]},{"given":"Fansheng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8316-7732","authenticated-orcid":false,"given":"Qian","family":"Ning","sequence":"additional","affiliation":[]},{"given":"Victor C. M.","family":"Leung","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,2]]},"reference":[{"key":"8913_CR1","doi-asserted-by":"crossref","unstructured":"Zheng Z, Zheng L, Yang Y (2017) A discriminatively learned cnn embedding for person reidentification. ACM Trans Multimedia Comput Commun Appl (TOMM) 14(1):1\u201320","DOI":"10.1145\/3159171"},{"key":"8913_CR2","doi-asserted-by":"crossref","unstructured":"Sun Y, Zheng L, Yang Y, Tian Q, Wang S (2018) Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: Proceedings of the European conference on computer vision (ECCV), pp 480\u2013496","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"8913_CR3","doi-asserted-by":"crossref","unstructured":"Wang G, Yuan Y, Chen X, Li J, Zhou X (2018) Learning discriminative features with multiple granularities for person re-identification. In: Proceedings of the 26th ACM international conference on multimedia, pp 274\u2013282","DOI":"10.1145\/3240508.3240552"},{"key":"8913_CR4","doi-asserted-by":"crossref","unstructured":"Chen T, Ding S, Xie J, Yuan Y, Chen W, Yang Y, Ren Z, Wang Z (2019) Abd-net: attentive but diverse person re-identification. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8351\u20138361","DOI":"10.1109\/ICCV.2019.00844"},{"key":"8913_CR5","doi-asserted-by":"crossref","unstructured":"He L, Liang J, Li H, Sun Z (2018) Deep spatial feature reconstruction for partial person re-identification: alignment-free approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7073\u20137082","DOI":"10.1109\/CVPR.2018.00739"},{"key":"8913_CR6","unstructured":"He L, Wang Y, Liu W, Zhao H, Sun Z, Feng J (2019) Foreground-aware pyramid reconstruction for alignment-free occluded person re-identification. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8450\u20138459"},{"key":"8913_CR7","unstructured":"Zheng L, Shen L, Tian L, Wang S, Bu J, Tian Q (2015) Person re-identification meets image search. arXiv preprint arXiv:1502.02171"},{"key":"8913_CR8","doi-asserted-by":"crossref","unstructured":"Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: European conference on computer vision, pp 17\u201335. Springer","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"8913_CR9","doi-asserted-by":"crossref","unstructured":"Wei L, Zhang S, Gao W, Tian Q (2018) Person transfer gan to bridge domain gap for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 79\u201388","DOI":"10.1109\/CVPR.2018.00016"},{"key":"8913_CR10","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"8913_CR11","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.jvcir.2019.01.010","volume":"60","author":"X Fan","year":"2019","unstructured":"Fan X, Jiang W, Luo H, Fei M (2019) Spherereid: Deep hypersphere manifold embedding for person re-identification. J Vis Commun Image Represent 60:51\u201358","journal-title":"J Vis Commun Image Represent"},{"issue":"6","key":"8913_CR12","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 SC (2021) Deep learning for person re-identification: a survey and outlook. IEEE Trans Pattern Anal Mach Intell 44(6):2872\u20132893","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8913_CR13","doi-asserted-by":"crossref","unstructured":"Luo H, Gu Y, Liao X, Lai S, Jiang W (2019) Bag of tricks and a strong baseline for deep person re-identification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"8913_CR14","doi-asserted-by":"crossref","unstructured":"Zhao H, Tian M, Sun S, Shao J, Yan J, Yi S, Wang X, Tang X (2017) Spindle net: Person re-identification with human body region guided feature decomposition and fusion. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1077\u20131085","DOI":"10.1109\/CVPR.2017.103"},{"key":"8913_CR15","doi-asserted-by":"crossref","unstructured":"Wei L, Zhang S, Yao H, Gao W, Tian Q (2017) Glad: Global-local-alignment descriptor for pedestrian retrieval. In: Proceedings of the 25th ACM international conference on multimedia, pp 420\u2013428","DOI":"10.1145\/3123266.3123279"},{"key":"8913_CR16","doi-asserted-by":"crossref","unstructured":"Song C, Huang Y, Ouyang W, Wang L (2018) Mask-guided contrastive attention model for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1179\u20131188","DOI":"10.1109\/CVPR.2018.00129"},{"key":"8913_CR17","doi-asserted-by":"crossref","unstructured":"Qi L, Huo J, Wang L, Shi Y, Gao Y (2018) Maskreid: A mask based deep ranking neural network for person re-identification. arXiv preprint arXiv:1804.03864","DOI":"10.1109\/ICME.2019.00092"},{"key":"8913_CR18","doi-asserted-by":"crossref","unstructured":"Kalayeh MM, Basaran E, G\u00f6kmen M, Kamasak ME, Shah M (2018) Human semantic parsing for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1062\u20131071","DOI":"10.1109\/CVPR.2018.00117"},{"key":"8913_CR19","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"8913_CR20","doi-asserted-by":"crossref","unstructured":"Girdhar R, Carreira J, Doersch C, Zisserman A (2019) Video action transformer network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 244\u2013253","DOI":"10.1109\/CVPR.2019.00033"},{"key":"8913_CR21","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European conference on computer vision, pp 213\u2013229. Springer","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"8913_CR22","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2020) Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159"},{"key":"8913_CR23","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie E, Wang W, Yu Z, Anandkumar A, Alvarez JM, Luo P (2021) Segformer: simple and efficient design for semantic segmentation with transformers. Adv Neural Inf Process Syst 34:12077\u201312090","journal-title":"Adv Neural Inf Process Syst"},{"key":"8913_CR24","unstructured":"Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille AL, Zhou Y (2021) Transunet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306"},{"key":"8913_CR25","doi-asserted-by":"crossref","unstructured":"Chen X, Yan B, Zhu J, Wang D, Yang X, Lu H (2021) Transformer tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8126\u20138135","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"8913_CR26","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al. (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"8913_CR27","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"8913_CR28","doi-asserted-by":"crossref","unstructured":"He S, Luo H, Wang P, Wang F, Li H, Jiang W (2021) Transreid: transformer-based object re-identification. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 15013\u201315022","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"8913_CR29","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255. Ieee","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"8913_CR30","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp 315\u2013323. JMLR Workshop and Conference Proceedings"},{"key":"8913_CR31","doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 815\u2013823","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"8913_CR32","doi-asserted-by":"crossref","unstructured":"Sun Y, Cheng C, Zhang Y, Zhang C, Zheng L, Wang Z, Wei Y (2020) Circle loss: a unified perspective of pair similarity optimization. 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"8913_CR33","doi-asserted-by":"crossref","unstructured":"Dikmen M, Akbas E, Huang TS, Ahuja N (2010) Pedestrian recognition with a learned metric. In: Asian conference on computer vision, pp 501\u2013512. Springer","DOI":"10.1007\/978-3-642-19282-1_40"},{"key":"8913_CR34","doi-asserted-by":"crossref","unstructured":"Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: a benchmark. In: Proceedings of the ieee international conference on computer vision, pp 1116\u20131124","DOI":"10.1109\/ICCV.2015.133"},{"key":"8913_CR35","doi-asserted-by":"crossref","unstructured":"Sun Y, Xu Q, Li Y, Zhang C, Li Y, Wang S, Sun J (2019) Perceive where to focus: learning visibility-aware part-level features for partial person re-identification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 393\u2013402","DOI":"10.1109\/CVPR.2019.00048"},{"key":"8913_CR36","doi-asserted-by":"crossref","unstructured":"Zheng Z, Yang X, Yu Z, Zheng L, Yang Y, Kautz J (2019) Joint discriminative and generative learning for person re-identification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2138\u20132147","DOI":"10.1109\/CVPR.2019.00224"},{"key":"8913_CR37","doi-asserted-by":"crossref","unstructured":"Hou R, Ma B, Chang H, Gu X, Shan S, Chen X (2019) Interaction-and-aggregation network for person re-identification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9317\u20139326","DOI":"10.1109\/CVPR.2019.00954"},{"key":"8913_CR38","doi-asserted-by":"crossref","unstructured":"Zhou K, Yang Y, Cavallaro A, Xiang T (2019) Omni-scale feature learning for person re-identification. In: Proceedings of the IEEE\/cvf international conference on computer vision, pp 3702\u20133712","DOI":"10.1109\/ICCV.2019.00380"},{"key":"8913_CR39","doi-asserted-by":"crossref","unstructured":"Fang P, Zhou J, Roy SK, Petersson L, Harandi M (2019) Bilinear attention networks for person retrieval. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8030\u20138039","DOI":"10.1109\/ICCV.2019.00812"},{"key":"8913_CR40","doi-asserted-by":"crossref","unstructured":"Zhu K, Guo H, Liu Z, Tang M, Wang J (2020) Identity-guided human semantic parsing for person re-identification. In: European conference on computer vision, pp 346\u2013363. Springer","DOI":"10.1007\/978-3-030-58580-8_21"},{"key":"8913_CR41","doi-asserted-by":"crossref","unstructured":"Chen X, Fu C, Zhao Y, Zheng F, Song J, Ji R, Yang Y (2020) Salience-guided cascaded suppression network for person re-identification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3300\u20133310","DOI":"10.1109\/CVPR42600.2020.00336"},{"key":"8913_CR42","doi-asserted-by":"crossref","unstructured":"Li Y, He J, Zhang T, Liu X, Zhang Y, Wu F (2021) 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","DOI":"10.1109\/CVPR46437.2021.00292"},{"key":"8913_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108567","volume":"126","author":"Y Chen","year":"2022","unstructured":"Chen Y, Wang H, Sun X, Fan B, Tang C, Zeng H (2022) Deep attention aware feature learning for person re-identification. Pattern Recogn 126:108567","journal-title":"Pattern Recogn"},{"key":"8913_CR44","unstructured":"Selvaraju RR, Das A, Vedantam R, Cogswell M, Parikh D, Batra D (2016) Grad-cam: Why did you say that? arXiv preprint arXiv:1611.07450"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08913-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08913-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08913-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T18:09:52Z","timestamp":1697566192000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08913-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,2]]},"references-count":44,"journal-issue":{"issue":"31","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["8913"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08913-2","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2023,9,2]]},"assertion":[{"value":"28 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interests regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}