{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:44:05Z","timestamp":1783611845529,"version":"3.55.0"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T00:00:00Z","timestamp":1737936000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T00:00:00Z","timestamp":1737936000000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s11263-025-02350-5","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T20:32:08Z","timestamp":1738009928000},"page":"3667-3688","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Dual-Space Video Person Re-identification"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2802-8139","authenticated-orcid":false,"given":"Jiaxu","family":"Leng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changjiang","family":"Kuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Gan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haosheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,27]]},"reference":[{"key":"2350_CR1","unstructured":"Bachmann, G., B\u00e9cigneul, G., & Ganea, O. (2020). Constant curvature graph convolutional networks. In International conference on machine learning, PMLR (pp. 486\u2013496)."},{"key":"2350_CR2","doi-asserted-by":"crossref","unstructured":"Bai, S., Ma, B., Chang, H., et\u00a0al. (2022). Salient-to-broad transition for video person re-identification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7339\u20137348).","DOI":"10.1109\/CVPR52688.2022.00719"},{"key":"2350_CR3","unstructured":"Chami, I., Ying, Z., R\u00e9, C., et\u00a0al. (2019). Hyperbolic graph convolutional neural networks. In Advances in neural information processing systems, Vol. 32."},{"key":"2350_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhou, Z., Huang, J., et\u00a0al. (2020). Frame-guided region-aligned representation for video person re-identification. In Proceedings of the AAAI conference on artificial intelligence (pp. 10591\u201310598).","DOI":"10.1609\/aaai.v34i07.6632"},{"key":"2350_CR5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3340428","author":"S Chen","year":"2023","unstructured":"Chen, S., Da, H., Wang, D. H., et al. (2023). Hasi: Hierarchical attention-aware Spatio-temporal interaction for video-based person re-identification. IEEE Transactions on Circuits and Systems for Video Technology. https:\/\/doi.org\/10.1109\/TCSVT.2023.3340428","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2350_CR6","doi-asserted-by":"crossref","unstructured":"Eom, C., Lee, G., Lee, J., et\u00a0al. (2021). Video-based person re-identification with spatial and temporal memory networks. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 12036\u201312045).","DOI":"10.1109\/ICCV48922.2021.01182"},{"key":"2350_CR7","doi-asserted-by":"crossref","unstructured":"Ermolov, A., Mirvakhabova, L., Khrulkov, V., et\u00a0al. (2022). Hyperbolic vision transformers: Combining improvements in metric learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7409\u20137419).","DOI":"10.1109\/CVPR52688.2022.00726"},{"key":"2350_CR8","doi-asserted-by":"crossref","unstructured":"Fu, Y., Wang, X., Wei, Y., et\u00a0al. (2019). Sta: Spatial-temporal attention for large-scale video-based person re-identification. In Proceedings of the AAAI conference on artificial intelligence (pp. pp 8287\u20138294).","DOI":"10.1609\/aaai.v33i01.33018287"},{"key":"2350_CR9","unstructured":"Ganea, O., B\u00e9cigneul, G., & Hofmann, T. (2018). Hyperbolic neural networks. In Advances in neural information processing systems, Vol. 31."},{"key":"2350_CR10","doi-asserted-by":"crossref","unstructured":"Gu, X., Chang, H., Ma, B., et\u00a0al. (2020). Appearance-preserving 3d convolution for video-based person re-identification. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16, pp. 228\u2013243. Springer.","DOI":"10.1007\/978-3-030-58536-5_14"},{"key":"2350_CR11","doi-asserted-by":"publisher","first-page":"3908","DOI":"10.1109\/TIP.2022.3175593","volume":"31","author":"X Gu","year":"2022","unstructured":"Gu, X., Chang, H., Ma, B., et al. (2022). Motion feature aggregation for video-based person re-identification. IEEE Transactions on Image Processing, 31, 3908\u20133919.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2350_CR12","doi-asserted-by":"crossref","unstructured":"He, T., Jin, X., Shen, X., et\u00a0al. (2021). Dense interaction learning for video-based person re-identification. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 1490\u20131501).","DOI":"10.1109\/ICCV48922.2021.00152"},{"key":"2350_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2350_CR14","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3318956","author":"S He","year":"2023","unstructured":"He, S., Chen, W., Wang, K., et al. (2023). Region generation and assessment network for occluded person re-identification. IEEE Transactions on Information Forensics and Security. https:\/\/doi.org\/10.1109\/TIFS.2023.3318956","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2350_CR15","unstructured":"Hermans, A., Beyer, L., & Leibe, B. (2017). In defense of the triplet loss for person re-identification. arXiv:1703.07737"},{"key":"2350_CR16","doi-asserted-by":"crossref","unstructured":"Hirzer, M,. Beleznai, C., Roth, P.M., et\u00a0al. (2011). Person re-identification by descriptive and discriminative classification. In Image analysis: 17th scandinavian conference, SCIA 2011, Ystad, Sweden, May 2011. Proceedings 17 (pp. 91\u2013102). Springer.","DOI":"10.1007\/978-3-642-21227-7_9"},{"key":"2350_CR17","doi-asserted-by":"crossref","unstructured":"Hou, R., Chang, H., Ma, B., et\u00a0al. (2020). Temporal complementary learning for video person re-identification. In Computer Vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXV 16 (pp. 388\u2013405). Springer.","DOI":"10.1007\/978-3-030-58595-2_24"},{"key":"2350_CR18","doi-asserted-by":"crossref","unstructured":"Hou, R., Chang, H., Ma, B., et\u00a0al. (2021) Bicnet-tks: Learning efficient spatial-temporal representation for video person re-identification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2014\u20132023).","DOI":"10.1109\/CVPR46437.2021.00205"},{"key":"2350_CR19","doi-asserted-by":"crossref","unstructured":"Hou, R., Ma, B., Chang, H., et\u00a0al. (2019). Vrstc: Occlusion-free video person re-identification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7183\u20137192).","DOI":"10.1109\/CVPR.2019.00735"},{"issue":"11","key":"2350_CR20","doi-asserted-by":"publisher","first-page":"2770","DOI":"10.1007\/s11263-022-01666-w","volume":"130","author":"Y Huang","year":"2022","unstructured":"Huang, Y., Fu, X., Li, L., et al. (2022). Learning degradation-invariant representation for robust real-world person re-identification. International Journal of Computer Vision, 130(11), 2770\u20132796.","journal-title":"International Journal of Computer Vision"},{"key":"2350_CR21","unstructured":"Kingma, D.P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv:1412.6980"},{"key":"2350_CR22","unstructured":"Kipf, T.N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv:1609.02907"},{"key":"2350_CR23","unstructured":"Law, M., Liao, R., Snell, J., et\u00a0al. (2019). Lorentzian distance learning for hyperbolic representations. In International conference on machine learning, PMLR (pp. 3672\u20133681)."},{"key":"2350_CR24","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.neucom.2023.03.003","volume":"536","author":"J Leng","year":"2023","unstructured":"Leng, J., Wang, H., Gao, X., et al. (2023). Where to look: Multi-granularity occlusion aware for video person re-identification. Neurocomputing, 536, 137\u2013151.","journal-title":"Neurocomputing"},{"key":"2350_CR25","doi-asserted-by":"crossref","unstructured":"Li, S., Bak, S., Carr, P., et\u00a0al. (2018). Diversity regularized spatiotemporal attention for video-based person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 369\u2013378).","DOI":"10.1109\/CVPR.2018.00046"},{"key":"2350_CR26","doi-asserted-by":"crossref","unstructured":"Li, S., Sun, L., Li, Q. (2023). Clip-reid: Exploiting vision-language model for image re-identification without concrete text labels. In Proceedings of the AAAI conference on artificial intelligence (pp. 1405\u20131413).","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"2350_CR27","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, J., Tian, Q., et\u00a0al. (2019a). Global-local temporal representations for video person re-identification. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 3958\u20133967).","DOI":"10.1109\/ICCV.2019.00406"},{"key":"2350_CR28","doi-asserted-by":"crossref","unstructured":"Li, S., Yu, H., & Hu, H. (2020b). Appearance and motion enhancement for video-based person re-identification. In Proceedings of the AAAI conference on artificial intelligence (pp. 11394\u201311401).","DOI":"10.1609\/aaai.v34i07.6802"},{"key":"2350_CR29","doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, S., & Huang, T. (2019b). Multi-scale 3d convolution network for video based person re-identification. In Proceedings of the AAAI conference on artificial intelligence (pp. 8618\u20138625).","DOI":"10.1609\/aaai.v33i01.33018618"},{"key":"2350_CR30","unstructured":"Liu, Q., Nickel, M., & Kiela, D. (2019a). Hyperbolic graph neural networks. In Advances in neural information processing systems, Vol. 32."},{"key":"2350_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yuan, Z., Zhou, W., et\u00a0al. (2019b). Spatial and temporal mutual promotion for video-based person re-identification. In Proceedings of the AAAI conference on artificial intelligence (pp. 8786\u20138793).","DOI":"10.1609\/aaai.v33i01.33018786"},{"key":"2350_CR32","doi-asserted-by":"crossref","unstructured":"Liu, J., Zha, Z.J., Wu, W., et\u00a0al. (2021a). Spatial-temporal correlation and topology learning for person re-identification in videos. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4370\u20134379).","DOI":"10.1109\/CVPR46437.2021.00435"},{"key":"2350_CR33","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhang, P., Yu, C., et\u00a0al. (2021b). Watching you: Global-guided reciprocal learning for video-based person re-identification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13334\u201313343).","DOI":"10.1109\/CVPR46437.2021.01313"},{"key":"2350_CR34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3296901","author":"L Liu","year":"2023","unstructured":"Liu, L., Yang, X., Wang, N., et al. (2023). Frequency information disentanglement network for video-based person re-identification. IEEE Transactions on Image Processing. https:\/\/doi.org\/10.1109\/TIP.2023.3296901","journal-title":"IEEE Transactions on Image Processing"},{"key":"2350_CR35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3271353","author":"X Liu","year":"2023","unstructured":"Liu, X., Yu, C., Zhang, P., et al. (2023). Deeply coupled convolution-transformer with spatial-temporal complementary learning for video-based person re-identification. IEEE Transactions on Neural Networks and Learning Systems. https:\/\/doi.org\/10.1109\/TNNLS.2023.3271353","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2350_CR36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3386914","author":"X Liu","year":"2024","unstructured":"Liu, X., Zhang, P., Yu, C., et al. (2024). A video is worth three views: Trigeminal transformers for video-based person re-identification. IEEE Transactions on Intelligent Transportation Systems. https:\/\/doi.org\/10.1109\/TITS.2024.3386914","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"6","key":"2350_CR37","doi-asserted-by":"publisher","first-page":"3260","DOI":"10.1109\/TPAMI.2020.3048039","volume":"44","author":"P Li","year":"2020","unstructured":"Li, P., Xu, Y., Wei, Y., et al. (2020). Self-correction for human parsing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(6), 3260\u20133271.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2350_CR38","doi-asserted-by":"crossref","unstructured":"Long, T., Mettes, P., Shen, H.T., et\u00a0al. (2020). Searching for actions on the hyperbole. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1141\u20131150).","DOI":"10.1109\/CVPR42600.2020.00122"},{"key":"2350_CR39","unstructured":"Nickel, M., & Kiela, D. (2017). Poincar\u00e9 embeddings for learning hierarchical representations. In Advances in neural information processing systems, Vol. 30."},{"key":"2350_CR40","doi-asserted-by":"publisher","first-page":"107300","DOI":"10.1016\/j.knosys.2021.107300","volume":"236","author":"H Pan","year":"2022","unstructured":"Pan, H., Bai, Y., He, Z., et al. (2022). Aagcn: Adjacency-aware graph convolutional network for person re-identification. Knowledge-Based Systems, 236, 107300.","journal-title":"Knowledge-Based Systems"},{"issue":"12","key":"2350_CR41","doi-asserted-by":"publisher","first-page":"7183","DOI":"10.1109\/TCSVT.2023.3276996","volume":"33","author":"H Pan","year":"2023","unstructured":"Pan, H., Liu, Q., Chen, Y., et al. (2023). Pose-aided video-based person re-identification via recurrent graph convolutional network. IEEE Transactions on Circuits and Systems for Video Technology, 33(12), 7183\u20137196.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2350_CR42","doi-asserted-by":"crossref","unstructured":"Park, J., Cho, J., Chang, H.J., et\u00a0al. (2021). Unsupervised hyperbolic representation learning via message passing auto-encoders. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5516\u20135526).","DOI":"10.1109\/CVPR46437.2021.00547"},{"key":"2350_CR43","doi-asserted-by":"crossref","unstructured":"Peng, W., Shi, J., Xia, Z., et\u00a0al. (2020). Mix dimension in Poincar\u00e9 geometry for 3d skeleton-based action recognition. In Proceedings of the 28th ACM international conference on multimedia (pp. 1432\u20131440).","DOI":"10.1145\/3394171.3413910"},{"issue":"12","key":"2350_CR44","doi-asserted-by":"publisher","first-page":"10023","DOI":"10.1109\/TPAMI.2021.3136921","volume":"44","author":"W Peng","year":"2021","unstructured":"Peng, W., Varanka, T., Mostafa, A., et al. (2021). Hyperbolic deep neural networks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12), 10023\u201310044.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2350_CR45","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al. (2021). Learning transferable visual models from natural language supervision. In International conference on machine learning, PMLR (pp. 8748\u20138763)."},{"issue":"6","key":"2350_CR46","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., et al. (2016). Faster r-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137\u20131149.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"2350_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3402666","volume":"16","author":"W Ruan","year":"2020","unstructured":"Ruan, W., Liang, C., Yu, Y., et al. (2020). Correlation discrepancy insight network for video re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 16(4), 1\u201321.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"2350_CR48","unstructured":"Shimizu, R., Mukuta, Y., & Harada, T. (2020). Hyperbolic neural networks++. arXiv:2006.08210"},{"key":"2350_CR49","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., et\u00a0al. (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":"2350_CR50","doi-asserted-by":"publisher","first-page":"7917","DOI":"10.1109\/TMM.2022.3231103","volume":"25","author":"Z Tang","year":"2022","unstructured":"Tang, Z., Zhang, R., Peng, Z., et al. (2022). Multi-stage spatio-temporal aggregation transformer for video person re-identification. IEEE Transactions on Multimedia, 25, 7917\u20137929.","journal-title":"IEEE Transactions on Multimedia"},{"key":"2350_CR51","doi-asserted-by":"crossref","unstructured":"Wang, T., Gong, S., Zhu, X., et\u00a0al. (2014). Person re-identification by video ranking. In Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV 13 (pp 688\u2013703). Springer.","DOI":"10.1007\/978-3-319-10593-2_45"},{"key":"2350_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, L., You, Y., et\u00a0al. (2018b). Resource aware person re-identification across multiple resolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 8042\u20138051).","DOI":"10.1109\/CVPR.2018.00839"},{"key":"2350_CR53","doi-asserted-by":"crossref","unstructured":"Wang, G., Yang, S., Liu, H., et\u00a0al. (2020). High-order information matters: Learning relation and topology for occluded person re-identification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 6449\u20136458).","DOI":"10.1109\/CVPR42600.2020.00648"},{"key":"2350_CR54","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, P., Gao, S., et\u00a0al. (2021). Pyramid spatial-temporal aggregation for video-based person re-identification. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 12026\u201312035).","DOI":"10.1109\/ICCV48922.2021.01181"},{"key":"2350_CR55","doi-asserted-by":"crossref","unstructured":"Wang, C., Zhang, Q., Huang, C., et\u00a0al. (2018a). Mancs: A multi-task attentional network with curriculum sampling for person re-identification. In Proceedings of the European conference on computer vision (ECCV) (pp. 365\u2013381).","DOI":"10.1007\/978-3-030-01225-0_23"},{"key":"2350_CR56","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lin, Y., Dong, X., et\u00a0al. (2018). Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5177\u20135186).","DOI":"10.1109\/CVPR.2018.00543"},{"key":"2350_CR57","doi-asserted-by":"publisher","first-page":"8821","DOI":"10.1109\/TIP.2020.3001693","volume":"29","author":"Y Wu","year":"2020","unstructured":"Wu, Y., Bourahla, O. E. F., Li, X., et al. (2020). Adaptive graph representation learning for video person re-identification. IEEE Transactions on Image Processing, 29, 8821\u20138830.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2350_CR58","doi-asserted-by":"crossref","unstructured":"Yan, Y., Qin, J., Chen, J., et\u00a0al. (2020). Learning multi-granular hypergraphs for video-based person re-identification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2899\u20132908).","DOI":"10.1109\/CVPR42600.2020.00297"},{"key":"2350_CR59","doi-asserted-by":"crossref","unstructured":"Yang, J., Zheng, W.S., Yang, Q., et\u00a0al. (2020) Spatial-temporal graph convolutional network for video-based person re-identification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3289\u20133299).","DOI":"10.1109\/CVPR42600.2020.00335"},{"key":"2350_CR60","unstructured":"Yang, M., Zhou, M., Li, Z., et\u00a0al. (2022). Hyperbolic graph neural networks: A review of methods and applications. arXiv:2202.13852"},{"issue":"6","key":"2350_CR61","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., et al. (2021). Deep learning for person re-identification: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(6), 2872\u20132893.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"2350_CR62","doi-asserted-by":"publisher","first-page":"1654","DOI":"10.1007\/s11263-019-01259-0","volume":"128","author":"J Yin","year":"2020","unstructured":"Yin, J., Wu, A., & Zheng, W. S. (2020). Fine-grained person re-identification. International Journal of Computer Vision, 128(6), 1654\u20131672.","journal-title":"International Journal of Computer Vision"},{"key":"2350_CR63","doi-asserted-by":"crossref","unstructured":"Yu, C., Liu, X., Wang, Y., et\u00a0al. (2024). Tf-clip: Learning text-free clip for video-based person re-identification. In Proceedings of the AAAI conference on artificial intelligence (pp. 6764\u20136772).","DOI":"10.1609\/aaai.v38i7.28500"},{"issue":"12","key":"2350_CR64","doi-asserted-by":"publisher","first-page":"8776","DOI":"10.1109\/TII.2022.3151766","volume":"18","author":"X Zang","year":"2022","unstructured":"Zang, X., Li, G., & Gao, W. (2022). Multidirection and multiscale pyramid in transformer for video-based pedestrian retrieval. IEEE Transactions on Industrial Informatics, 18(12), 8776\u20138785.","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"2350_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Lan, C., Zeng, W., et\u00a0al. (2020). Multi-granularity reference-aided attentive feature aggregation for video-based person re-identification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10407\u201310416).","DOI":"10.1109\/CVPR42600.2020.01042"},{"key":"2350_CR66","unstructured":"Zhang, T., Wei, L., Xie, L., et\u00a0al. (2021b). Spatiotemporal transformer for video-based person re-identification. arXiv:2103.16469"},{"key":"2350_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, H., & Liu, S. (2021d). Person re-identification using heterogeneous local graph attention networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12136\u201312145).","DOI":"10.1109\/CVPR46437.2021.01196"},{"key":"2350_CR68","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1007\/s11263-021-01461-z","volume":"129","author":"S Zhang","year":"2021","unstructured":"Zhang, S., Chen, D., Yang, J., et al. (2021). Guided attention in CNNs for occluded pedestrian detection and re-identification. International Journal of Computer Vision, 129, 1875\u20131892.","journal-title":"International Journal of Computer Vision"},{"key":"2350_CR69","doi-asserted-by":"publisher","first-page":"3823","DOI":"10.1007\/s11263-024-02057-z","volume":"132","author":"L Zhang","year":"2024","unstructured":"Zhang, L., Fu, X., Huang, F., et al. (2024). An open-world, diverse, cross-spatial-temporal benchmark for dynamic wild person re-identification. International Journal of Computer Vision, 132, 3823\u20133846.","journal-title":"International Journal of Computer Vision"},{"key":"2350_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, X., Shi, C., et al. (2021). Hyperbolic graph attention network. IEEE Transactions on Big Data, 8(6), 1690\u20131701.","DOI":"10.1109\/TBDATA.2021.3081431"},{"key":"2350_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, H., Liu, S., et al. (2021). Part-guided graph convolution networks for person re-identification. Pattern Recognition, 120, 108155.","DOI":"10.1016\/j.patcog.2021.108155"},{"key":"2350_CR72","doi-asserted-by":"crossref","unstructured":"Zheng, L., Bie, Z., Sun, Y., et\u00a0al. (2016). Mars: A video benchmark for large-scale person re-identification. In Computer Vision\u2014ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VI 14 (pp. 868\u2013884). Springer.","DOI":"10.1007\/978-3-319-46466-4_52"},{"key":"2350_CR73","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., et\u00a0al. (2020). Random erasing data augmentation. In Proceedings of the AAAI conference on artificial intelligence (pp. 13001\u201313008).","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"2350_CR74","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Huang, Y., Wang, W., et\u00a0al. (2017). See the forest for the trees: Joint spatial and temporal recurrent neural networks for video-based person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4747\u20134756).","DOI":"10.1109\/CVPR.2017.717"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02350-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02350-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02350-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T06:56:41Z","timestamp":1746860201000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02350-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,27]]},"references-count":74,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["2350"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02350-5","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,27]]},"assertion":[{"value":"12 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}