{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:45:08Z","timestamp":1757612708409,"version":"3.44.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T00:00:00Z","timestamp":1741824000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T00:00:00Z","timestamp":1741824000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Science and Technology Research Program of Chongqing Municipal Education Commission","award":["KJQN202301902","KJQN202301902","KJQN202301902","KJQN202301902","KJQN202301902"],"award-info":[{"award-number":["KJQN202301902","KJQN202301902","KJQN202301902","KJQN202301902","KJQN202301902"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s00530-025-01748-y","type":"journal-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T12:04:44Z","timestamp":1741867484000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DSFAT: a dual-stream framework assisted by textual information for person re-identification in real scenes"],"prefix":"10.1007","volume":"31","author":[{"given":"Xuanrui","family":"Xiong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haihong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,13]]},"reference":[{"issue":"12","key":"1748_CR1","doi-asserted-by":"publisher","first-page":"9342","DOI":"10.1109\/JIOT.2021.3084978","volume":"9","author":"M Fu","year":"2021","unstructured":"Fu, M., Sun, S., Gao, H., Wang, D., Tong, X., Liu, Q., Liang, Q.: Improving person reidentification using a self-focusing network in internet of things. IEEE Internet Things J. 9(12), 9342\u20139353 (2021)","journal-title":"IEEE Internet Things J."},{"issue":"15","key":"1748_CR2","doi-asserted-by":"publisher","first-page":"13865","DOI":"10.1109\/JIOT.2023.3263240","volume":"10","author":"X Liu","year":"2023","unstructured":"Liu, X., Zhou, Z., Niu, C., Wu, Q.: Visual-textual alignment for generalizable person reidentification in internet of things. IEEE Internet Things J. 10(15), 13865\u201313875 (2023)","journal-title":"IEEE Internet Things J."},{"key":"1748_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109636","volume":"141","author":"Q Liu","year":"2023","unstructured":"Liu, Q., He, X., Teng, Q., Qing, L., Chen, H.: Bdnet: a bert-based dual-path network for text-to-image cross-modal person re-identification. Pattern Recognit. 141, 109636 (2023)","journal-title":"Pattern Recognit."},{"key":"1748_CR4","unstructured":"Zhang, T., Zhang, S., Jia, W.: Person reidentification based on adaptive relation attention network in intelligent monitoring system for the iob. IEEE Trans. Eng. Manag. (2022)"},{"issue":"6","key":"1748_CR5","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(6), 2872\u20132893 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1748_CR6","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)","journal-title":"Image Vis. Comput."},{"key":"1748_CR7","doi-asserted-by":"crossref","unstructured":"Li, H., Wu, G., Zheng, W.-S.: Combined depth space based architecture search for person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6729\u20136738 (2021)","DOI":"10.1109\/CVPR46437.2021.00666"},{"issue":"9","key":"1748_CR8","doi-asserted-by":"publisher","first-page":"5056","DOI":"10.1109\/TPAMI.2021.3069237","volume":"44","author":"K Zhou","year":"2021","unstructured":"Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Learning generalisable omni-scale representations for person re-identification. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5056\u20135069 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1748_CR9","doi-asserted-by":"crossref","unstructured":"Rao, H., Miao, C.: Transg: transformer-based skeleton graph prototype contrastive learning with structure-trajectory prompted reconstruction for person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22118\u201322128 (2023)","DOI":"10.1109\/CVPR52729.2023.02118"},{"issue":"3","key":"1748_CR10","doi-asserted-by":"publisher","first-page":"1624","DOI":"10.1109\/TCSVT.2021.3073718","volume":"32","author":"H Li","year":"2021","unstructured":"Li, H., Xiao, J., Sun, M., Lim, E.G., Zhao, Y.: Transformer-based language-person search with multiple region slicing. IEEE Trans. Circuits Syst. Video Technol. 32(3), 1624\u20131633 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1748_CR11","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhou, Y., Zheng, Z., Wang, Y., Zhu, L., Wu, Y.: Towards unified text-based person retrieval: a large-scale multi-attribute and language search benchmark. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 4492\u20134501 (2023)","DOI":"10.1145\/3581783.3611709"},{"issue":"20","key":"1748_CR12","doi-asserted-by":"publisher","first-page":"15059","DOI":"10.1109\/JIOT.2020.3036821","volume":"8","author":"M Fu","year":"2020","unstructured":"Fu, M., Sun, S., Liang, Q., Tong, X., Liu, Q.: Exciting-inhibition network for person reidentification in internet of things. IEEE Internet Things J. 8(20), 15059\u201315069 (2020)","journal-title":"IEEE Internet Things J."},{"key":"1748_CR13","doi-asserted-by":"crossref","unstructured":"Yuan, B., Chen, B., Tan, Z., Shao, X., Bao, B.K.: Unbiased feature enhancement framework for cross-modality person re-identification. Multim. Syst. 1\u201311 (2022)","DOI":"10.1007\/s00530-021-00872-9"},{"key":"1748_CR14","doi-asserted-by":"publisher","first-page":"5907","DOI":"10.1109\/TIP.2024.3477351","volume":"33","author":"T Liu","year":"2024","unstructured":"Liu, T., Lam, K.M., Bao, B.K.: Injecting text clues for improving anomalous event detection from weakly labeled videos. IEEE Trans. Image Process. 33, 5907\u20135920 (2024)","journal-title":"IEEE Trans. Image Process."},{"key":"1748_CR15","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.patcog.2019.06.006","volume":"95","author":"Y Lin","year":"2019","unstructured":"Lin, Y., Zheng, L., Zheng, Z., Wu, Y., Hu, Z., Yan, C., Yang, Y.: Improving person re-identification by attribute and identity learning. Pattern Recognit. 95, 151\u2013161 (2019)","journal-title":"Pattern Recognit."},{"key":"1748_CR16","doi-asserted-by":"crossref","unstructured":"Han, K., Guo, J., Zhang, C., Zhu, M.: Attribute-aware attention model for fine-grained representation learning. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 2040\u20132048 (2018)","DOI":"10.1145\/3240508.3240550"},{"key":"1748_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Wang, Z., Fu, Y., Feng, R., Jiang, Y.-G., Xue, X.: Adaptively weighted multi-task deep network for person attribute classification. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1636\u20131644 (2017)","DOI":"10.1145\/3123266.3123424"},{"key":"1748_CR18","doi-asserted-by":"publisher","first-page":"4376","DOI":"10.1109\/TMM.2020.3042068","volume":"23","author":"Y Shi","year":"2020","unstructured":"Shi, Y., Wei, Z., Ling, H., Wang, Z., Shen, J., Li, P.: Person retrieval in surveillance videos via deep attribute mining and reasoning. IEEE Trans. Multim. 23, 4376\u20134387 (2020)","journal-title":"IEEE Trans. Multim."},{"key":"1748_CR19","doi-asserted-by":"crossref","unstructured":"Nguyen, B.X., Nguyen, B.D., Do, T., Tjiputra, E., Tran, Q.D., Nguyen, A.: Graph-based person signature for person re-identifications. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3492\u20133501 (2021)","DOI":"10.1109\/CVPRW53098.2021.00388"},{"issue":"6","key":"1748_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3597434","volume":"19","author":"G Tang","year":"2023","unstructured":"Tang, G., Gao, X., Chen, Z.: Learning semantic representation on visual attribute graph for person re-identification and beyond. ACM Trans. Multim. Comput. Commun. Appl. 19(6), 1\u201320 (2023)","journal-title":"ACM Trans. Multim. Comput. Commun. Appl."},{"key":"1748_CR21","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhu, X., Gong, S., Li, W.: Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2275\u20132284 (2018)","DOI":"10.1109\/CVPR.2018.00242"},{"key":"1748_CR22","doi-asserted-by":"crossref","unstructured":"Jing, Y., Si, C., Wang, J., Wang, W., Wang, L., Tan, T.: Pose-guided multi-granularity attention network for text-based person search. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11189\u201311196 (2020)","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"1748_CR23","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Yang, W., Wang, X.: Identity-aware textual-visual matching with latent co-attention. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1890\u20131899 (2017)","DOI":"10.1109\/ICCV.2017.209"},{"key":"1748_CR24","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Zhou, B., Wang, X.: Person search with natural language description. IEEE Comput. Soc. (2017)","DOI":"10.1109\/CVPR.2017.551"},{"issue":"2","key":"1748_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3383184","volume":"16","author":"Z Zheng","year":"2020","unstructured":"Zheng, Z., Zheng, L., Garrett, M., Yang, Y., Xu, M., Shen, Y.-D.: Dual-path convolutional image-text embeddings with instance loss. ACM Trans. Multim. Comput. Commun. Appl. 16(2), 1\u201323 (2020)","journal-title":"ACM Trans. Multim. Comput. Commun. Appl."},{"key":"1748_CR26","doi-asserted-by":"crossref","unstructured":"Han, X., He, S., Zhang, L., Xiang, T.: Text-based person search with limited data. arXiv:2110.10807 (2021)","DOI":"10.5244\/C.35.10"},{"key":"1748_CR27","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.aiopen.2022.10.001","volume":"3","author":"T Lin","year":"2022","unstructured":"Lin, T., Wang, Y., Liu, X., Qiu, X.: A survey of transformers. AI Open 3, 111\u2013132 (2022)","journal-title":"AI Open"},{"key":"1748_CR28","unstructured":"Xiang, S., Gao, J., Guan, M., Ruan, J., Zhou, C., Liu, T., Qian, D., Fu, Y.: Learning robust visual-semantic embedding for generalizable person re-identification. arXiv:2304.09498 (2023)"},{"key":"1748_CR29","doi-asserted-by":"crossref","unstructured":"Qin, Z., Liu, P., Liu, Y., Duan, H., Li, F., Wang, H.: Pedestrian re-identification based on swin transformer. In: 2022 3rd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), pp. 123\u2013129. IEEE (2022)","DOI":"10.1109\/ICBAIE56435.2022.9985893"},{"key":"1748_CR30","doi-asserted-by":"crossref","unstructured":"Jiang, D., Ye, M.: Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2787\u20132797 (2023)","DOI":"10.1109\/CVPR52729.2023.00273"},{"issue":"7","key":"1748_CR31","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1109\/TPAMI.2018.2846566","volume":"41","author":"F Radenovi\u0107","year":"2018","unstructured":"Radenovi\u0107, F., Tolias, G., Chum, O.: Fine-tuning cnn image retrieval with no human annotation. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1655\u20131668 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1748_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, H.: Deep cross-modal projection learning for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 686\u2013701 (2018)","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"1748_CR33","unstructured":"Gao, C., Cai, G., Jiang, X., Zheng, F., Zhang, J., Gong, Y., Peng, P., Guo, X., Sun, X.: Contextual non-local alignment over full-scale representation for text-based person search. arXiv:2101.03036 (2021)"},{"key":"1748_CR34","doi-asserted-by":"crossref","unstructured":"Sarafianos, N., Xu, X., Kakadiaris, I.A.: Adversarial representation learning for text-to-image matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5814\u20135824 (2019)","DOI":"10.1109\/ICCV.2019.00591"},{"key":"1748_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Z., Fang, Z., Wang, J., Yang, Y.: Vitaa: Visual-textual attributes alignment in person search by natural language. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XII 16, pp. 402\u2013420. Springer (2020)","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"1748_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, A., Wang, Z., Li, Y., Wan, X., Jin, J., Wang, T., Hu, F., Hua, G.: Dssl: deep surroundings-person separation learning for text-based person retrieval. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 209\u2013217 (2021)","DOI":"10.1145\/3474085.3475369"},{"key":"1748_CR37","unstructured":"Ding, Z., Ding, C., Shao, Z., Tao, D.: Semantically self-aligned network for text-to-image part-aware person re-identification. arxiv (2021). arXiv:2107.12666 (2021)"},{"key":"1748_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhu, A., Xue, J., Wan, X., Liu, C., Wang, T., Li, Y.: Look before you leap: Improving text-based person retrieval by learning a consistent cross-modal common manifold. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1984\u20131992 (2022)","DOI":"10.1145\/3503161.3548166"},{"key":"1748_CR39","doi-asserted-by":"crossref","unstructured":"Li, S., Cao, M., Zhang, M.: Learning semantic-aligned feature representation for text-based person search. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2724\u20132728. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746846"},{"key":"1748_CR40","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.neucom.2022.04.081","volume":"494","author":"Y Chen","year":"2022","unstructured":"Chen, Y., Zhang, G., Lu, Y., Wang, Z., Zheng, Y.: Tipcb: a simple but effective part-based convolutional baseline for text-based person search. Neurocomputing 494, 171\u2013181 (2022)","journal-title":"Neurocomputing"},{"key":"1748_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhu, A., Xue, J., Wan, X., Liu, C., Wang, T., Li, Y.: Caibc: capturing all-round information beyond color for text-based person retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5314\u20135322 (2022)","DOI":"10.1145\/3503161.3548057"},{"key":"1748_CR42","doi-asserted-by":"crossref","unstructured":"Farooq, A., Awais, M., Kittler, J., Khalid, S.S.: Axm-net: implicit cross-modal feature alignment for person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 4477\u20134485 (2022)","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"1748_CR43","doi-asserted-by":"crossref","unstructured":"Shao, Z., Zhang, X., Fang, M., Lin, Z., Wang, J., Ding, C.: Learning granularity-unified representations for text-to-image person re-identification. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5566\u20135574 (2022)","DOI":"10.1145\/3503161.3548028"},{"key":"1748_CR44","doi-asserted-by":"crossref","unstructured":"Shu, X., Wen, W., Wu, H., Chen, K., Song, Y., Qiao, R., Ren, B., Wang, X.: See finer, see more: Implicit modality alignment for text-based person retrieval. In: European Conference on Computer Vision, pp. 624\u2013641. Springer (2022)","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"1748_CR45","doi-asserted-by":"crossref","unstructured":"Yan, S., Dong, N., Zhang, L., Tang, J.: Clip-driven fine-grained text-image person re-identification. IEEE Trans. Image Process. (2023)","DOI":"10.1109\/TIP.2023.3327924"},{"key":"1748_CR46","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1109\/TIP.2023.3337653","volume":"33","author":"S He","year":"2023","unstructured":"He, S., Luo, H., Jiang, W., Jiang, X., Ding, H.: Vgsg: vision-guided semantic-group network for text-based person search. IEEE Trans. Image Process. 33, 163\u2013176 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"1748_CR47","doi-asserted-by":"crossref","unstructured":"Yan, S., Tang, H., Zhang, L., Tang, J.: Image-specific information suppression and implicit local alignment for text-based person search. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3310118"},{"issue":"3","key":"1748_CR48","first-page":"329","volume":"18","author":"A Dey","year":"2024","unstructured":"Dey, A., Biswas, S., Abualigah, L.: Efficient violence recognition in video streams using resdlcnn-gru attention network. ECTI Trans. Comput. Inform. Technol. 18(3), 329\u2013341 (2024)","journal-title":"ECTI Trans. Comput. Inform. Technol."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01748-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01748-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01748-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T15:05:01Z","timestamp":1756998301000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01748-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,13]]},"references-count":48,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["1748"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01748-y","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2025,3,13]]},"assertion":[{"value":"19 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2025","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"155"}}