{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T08:45:18Z","timestamp":1792745118453,"version":"4.5.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T00:00:00Z","timestamp":1736380800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T00:00:00Z","timestamp":1736380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s00138-025-01659-y","type":"journal-article","created":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T08:31:45Z","timestamp":1736411505000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Personvit: large-scale self-supervised vision transformer for person re-identification"],"prefix":"10.1007","volume":"36","author":[{"given":"Bin","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,9]]},"reference":[{"key":"1659_CR1","unstructured":"Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)"},{"key":"1659_CR2","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":"1659_CR3","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1659_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1659_CR5","doi-asserted-by":"crossref","unstructured":"Zhu, K., Guo, H., Yan, T., Zhu, Y., Wang, J., Tang, M.: Pass: part-aware self-supervised pre-training for person re-identification. arXiv preprint arXiv:2203.03931 (2022)","DOI":"10.1007\/978-3-031-19781-9_12"},{"key":"1659_CR6","doi-asserted-by":"crossref","unstructured":"Fu, D., Chen, D., Bao, J., Yang, H., Yuan, L., Zhang, L., Li, H., Chen, D.: Unsupervised pre-training for person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14750\u201314759 (2021)","DOI":"10.1109\/CVPR46437.2021.01451"},{"key":"1659_CR7","unstructured":"Luo, H., Wang, P., Xu, Y., Ding, F., Zhou, Y., Wang, F., Li, H., Jin, R.: Self-supervised pre-training for transformer-based person re-identification. arXiv preprint arXiv:2111.12084 (2021)"},{"key":"1659_CR8","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. arXiv preprint arXiv:2104.14294 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"1659_CR9","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 (ECCV), pp. 480\u2013496 (2018)","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"1659_CR10","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"1659_CR11","unstructured":"Bao, H., Dong, L., Wei, F.: Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"1659_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1659_CR13","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Bao, J., Yao, Z., Dai, Q., Hu, H.: Simmim: a simple framework for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"1659_CR14","doi-asserted-by":"crossref","unstructured":"Wei, L., Zhang, S., Gao, W., Tian, Q.: 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 (2018)","DOI":"10.1109\/CVPR.2018.00016"},{"key":"1659_CR15","doi-asserted-by":"crossref","unstructured":"Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: A benchmark. In: Computer Vision, IEEE International Conference on Computer Vision, pp. 1116\u20131124 (2015)","DOI":"10.1109\/ICCV.2015.133"},{"key":"1659_CR16","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by gan improve the person re-identification baseline in vitro. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3754\u20133762 (2017)","DOI":"10.1109\/ICCV.2017.405"},{"key":"1659_CR17","doi-asserted-by":"crossref","unstructured":"Miao, J., Wu, Y., Liu, P., Ding, Y., Yang, Y.: Pose-guided feature alignment for occluded person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 542\u2013551 (2019)","DOI":"10.1109\/ICCV.2019.00063"},{"issue":"11","key":"1659_CR18","doi-asserted-by":"publisher","first-page":"4037","DOI":"10.1109\/TPAMI.2020.2992393","volume":"43","author":"L Jing","year":"2020","unstructured":"Jing, L., Tian, Y.: Self-supervised visual feature learning with deep neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 4037\u20134058 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1659_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1659_CR20","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"1659_CR21","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9640\u20139649 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"1659_CR22","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"1659_CR23","first-page":"21271","volume":"33","author":"J-B Grill","year":"2020","unstructured":"Grill, J.-B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila Pires, B., Guo, Z., Gheshlaghi Azar, M., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1659_CR24","unstructured":"Xie, Z., Lin, Y., Yao, Z., Zhang, Z., Dai, Q., Cao, Y., Hu, H.: Self-supervised learning with swin transformers. arXiv preprint arXiv:2105.04553 (2021)"},{"key":"1659_CR25","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training (2018)"},{"key":"1659_CR26","first-page":"13165","volume":"34","author":"Z Li","year":"2021","unstructured":"Li, Z., Chen, Z., Yang, F., Li, W., Zhu, Y., Zhao, C., Deng, R., Wu, L., Zhao, R., Tang, M., et al.: MST: masked self-supervised transformer for visual representation. Adv. Neural Inf. Process. Syst. 34, 13165\u201313176 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1659_CR27","unstructured":"Zhou, J., Wei, C., Wang, H., Shen, W., Xie, C., Yuille, A., Kong, T.: ibot: image bert pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)"},{"key":"1659_CR28","doi-asserted-by":"crossref","unstructured":"Assran, M., Caron, M., Misra, I., Bojanowski, P., Bordes, F., Vincent, P., Joulin, A., Rabbat, M., Ballas, N.: Masked siamese networks for label-efficient learning. arXiv preprint arXiv:2204.07141 (2022)","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"1659_CR29","doi-asserted-by":"crossref","unstructured":"Zheng, L., Zhang, H., Sun, S., Chandraker, M., Yang, Y., Tian, Q.: Person re-identification in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1367\u20131376 (2017)","DOI":"10.1109\/CVPR.2017.357"},{"key":"1659_CR30","doi-asserted-by":"crossref","unstructured":"Qian, X., Fu, Y., Jiang, Y.-G., Xiang, T., Xue, X.: Multi-scale deep learning architectures for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5399\u20135408 (2017)","DOI":"10.1109\/ICCV.2017.577"},{"key":"1659_CR31","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":"1659_CR32","doi-asserted-by":"crossref","unstructured":"Song, C., Huang, Y., Ouyang, W., Wang, L.: Mask-guided contrastive attention model for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1179\u20131188 (2018)","DOI":"10.1109\/CVPR.2018.00129"},{"key":"1659_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, L., Li, X., Zhuang, Y., Wang, J.: Deeply-learned part-aligned representations for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3219\u20133228 (2017)","DOI":"10.1109\/ICCV.2017.349"},{"key":"1659_CR34","doi-asserted-by":"crossref","unstructured":"Suh, Y., Wang, J., Tang, S., Mei, T., Mu\u00a0Lee, K.: Part-aligned bilinear representations for person re-identification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 402\u2013419 (2018)","DOI":"10.1007\/978-3-030-01264-9_25"},{"key":"1659_CR35","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: 2018 ACM Multimedia Conference on Multimedia Conference, pp. 274\u2013282 (2018). ACM","DOI":"10.1145\/3240508.3240552"},{"key":"1659_CR36","doi-asserted-by":"crossref","unstructured":"He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W.: Transreid: transformer-based object re-identification. In: Proceedings of the IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"1659_CR37","doi-asserted-by":"crossref","unstructured":"Chen, W., Xu, X., Jia, J., Luo, H., Wang, Y., Wang, F., Jin, R., Sun, X.: Beyond appearance: a semantic controllable self-supervised learning framework for human-centric visual tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15050\u201315061 (2023)","DOI":"10.1109\/CVPR52729.2023.01445"},{"key":"1659_CR38","doi-asserted-by":"crossref","unstructured":"Hu, H., Dong, X., Bao, J., Chen, D., Yuan, L., Chen, D., Li, H.: PersonMAE: person re-identification pre-training with masked auto encoders. IEEE Transactions on Multimedia (2024)","DOI":"10.1109\/TMM.2024.3405649"},{"key":"1659_CR39","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.neucom.2022.07.085","volume":"508","author":"N Sharma","year":"2022","unstructured":"Sharma, N., Dhiman, C., Indu, S.: Pedestrian intention prediction for autonomous vehicles: a comprehensive survey. Neurocomputing 508, 120\u2013152 (2022). https:\/\/doi.org\/10.1016\/j.neucom.2022.07.085","journal-title":"Neurocomputing"},{"issue":"22","key":"1659_CR40","doi-asserted-by":"publisher","first-page":"27540","DOI":"10.1109\/JSEN.2023.3317426","volume":"23","author":"N Sharma","year":"2023","unstructured":"Sharma, N., Dhiman, C., Indu, S.: Visual-motion-interaction-guided pedestrian intention prediction framework. IEEE Sensors J. 23(22), 27540\u201327548 (2023). https:\/\/doi.org\/10.1109\/JSEN.2023.3317426","journal-title":"IEEE Sensors J."},{"key":"1659_CR41","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3391898","author":"N Sharma","year":"2024","unstructured":"Sharma, N., Dhiman, C., Indu, S.: Progressive contextual trajectory prediction with adaptive gating and fuzzy logic integration. IEEE Trans. Intell. Veh. (2024). https:\/\/doi.org\/10.1109\/TIV.2024.3391898","journal-title":"IEEE Trans. Intell. Veh."},{"key":"1659_CR42","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"},{"key":"1659_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104394","volume":"119","author":"Z Ming","year":"2022","unstructured":"Ming, Z., Zhu, M., Wang, X., Zhu, J., Cheng, J., Gao, C., Yang, Y., Wei, X.: Deep learning-based person re-identification methods: a survey and outlook of recent works. Image Vis. Comput. 119, 104394 (2022). https:\/\/doi.org\/10.1016\/j.imavis.2022.104394","journal-title":"Image Vis. Comput."},{"key":"1659_CR44","unstructured":"Zhu, K., Guo, H., Zhang, S., Wang, Y., Huang, G., Qiao, H., Liu, J., Wang, J., Tang, M.: Aaformer: auto-Aligned transformer for person re-identification. arXiv preprint arXiv:2104.00921 (2021)"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-025-01659-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-025-01659-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-025-01659-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T04:19:37Z","timestamp":1741839577000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-025-01659-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,9]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["1659"],"URL":"https:\/\/doi.org\/10.1007\/s00138-025-01659-y","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,9]]},"assertion":[{"value":"9 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 December 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"32"}}