{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:07:46Z","timestamp":1772644066352,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:00:00Z","timestamp":1765497600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:00:00Z","timestamp":1765497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"\u56fd\u5bb6\u81ea\u7136\u79d1\u5b66\u57fa\u91d1\u59d4\u5458\u4f1a","doi-asserted-by":"crossref","award":["62076137"],"award-info":[{"award-number":["62076137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"\u56fd\u5bb6\u81ea\u7136\u79d1\u5b66\u57fa\u91d1\u59d4\u5458\u4f1a","doi-asserted-by":"crossref","award":["62076137"],"award-info":[{"award-number":["62076137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Open Project of Jiangsu Center of Applied Mathematics"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s00371-025-04213-z","type":"journal-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T05:57:47Z","timestamp":1765519067000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adt-net: adaptive transformation-driven text-based person search network for enhancing cross-modal retrieval robustness"],"prefix":"10.1007","volume":"42","author":[{"given":"Zimo","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanxiao","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoqing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,12]]},"reference":[{"key":"4213_CR1","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Zhou, B., Yue, D., Wang, X.: \u201cPerson search with natural language description,\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1970\u20131979 (2017)","DOI":"10.1109\/CVPR.2017.551"},{"key":"4213_CR2","doi-asserted-by":"publisher","first-page":"4555","DOI":"10.1109\/TIP.2023.3279673","volume":"32","author":"G Zhang","year":"2023","unstructured":"Zhang, G., Liu, J., Chen, Y., et al.: Multi-biometric unified network for cloth-changing person re-identification. IEEE Trans. Image Process. 32, 4555\u20134566 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"4213_CR3","unstructured":"Gao, S., Wang, J., Lu, H., Liu, Z.: Pose-guided visible part matching for occluded person reid, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11 744\u201311 752 (2020)"},{"key":"4213_CR4","doi-asserted-by":"crossref","unstructured":"Bai, Yang, et al.: Rasa: Relation and sensitivity aware representation learning for text-based person search. arXiv preprint arXiv:2305.13653 (2023)","DOI":"10.24963\/ijcai.2023\/62"},{"key":"4213_CR5","doi-asserted-by":"crossref","unstructured":"Aggarwal, S., Radhakrishnan, V.B., Chakraborty, A.: Text-based person search via attribute-aided matching[C]\/\/Proceedings of the IEEE\/CVF winter conference on applications of computer vision: 2617\u20132625 (2020)","DOI":"10.1109\/WACV45572.2020.9093640"},{"key":"4213_CR6","unstructured":"Eom, C., Lee, G., Lee, J., Ham, B.: Video-based person re-identification with spatial and temporal mem- ory networks, in Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12 036\u2013 12 045 (2021)"},{"key":"4213_CR7","unstructured":"Zhang, T., Wei, L., Xie, L., Zhuang, Z., Zhang, Y., Li, B., Tian, Q.: \u201cSpatiotemporal transformer for video-based person re-identification,\u201d arXiv preprint arXiv:2103.16469, (2021)"},{"key":"4213_CR8","unstructured":"Gao, J., Nevatia, R.: Revisiting temporal modeling for video-based person reid[J]. arXiv preprint arXiv:1805.02104, (2018)"},{"issue":"12","key":"4213_CR9","doi-asserted-by":"publisher","first-page":"3646","DOI":"10.1109\/TCSVT.2018.2883995","volume":"29","author":"Z Liu","year":"2018","unstructured":"Liu, Z., Wang, Y., Li, A.: Hierarchical integration of rich features for video-based person re-identification[J]. IEEE Trans. Circuits Syst. Video Technol. 29(12), 3646\u20133659 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"4213_CR10","unstructured":"Ding, Z., Ding, C., Shao, Z., Tao, D.: Semantically self-aligned network for text-to-image part-aware per- son re-identification, arXiv preprint arXiv:2107.12666, (2021)"},{"issue":"12","key":"4213_CR11","doi-asserted-by":"publisher","first-page":"17973","DOI":"10.1109\/TNNLS.2023.3310118","volume":"35","author":"S Yan","year":"2024","unstructured":"Yan, S., Tang, H., Zhang, L., Tang, J.: Image-Specific Information Suppression and Implicit Local Alignment for Text-Based Person Search. IEEE Transactions on Neural Networks and Learning Systems 35(12), 17973\u201317986 (2024). https:\/\/doi.org\/10.1109\/TNNLS.2023.3310118","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"4213_CR12","doi-asserted-by":"publisher","first-page":"6032","DOI":"10.1109\/TIP.2023.3327924","volume":"32","author":"S Yan","year":"2023","unstructured":"Yan, S., Dong, N., Zhang, L., Tang, J.: CLIP-Driven Fine-Grained Text-Image Person Re-Identification. IEEE Trans. Image Process. 32, 6032\u20136046 (2023). https:\/\/doi.org\/10.1109\/TIP.2023.3327924","journal-title":"IEEE Trans. Image Process."},{"key":"4213_CR13","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":"4213_CR14","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\u2013 1992 (2022)","DOI":"10.1145\/3503161.3548166"},{"key":"4213_CR15","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision, International Conference on Machine Learning. PMLR: 8748\u20138763 (2021)"},{"key":"4213_CR16","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"},{"key":"4213_CR17","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. Springer, pp. 624\u2013641 (2022)","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"4213_CR18","doi-asserted-by":"crossref","unstructured":"Aggarwal, S., Radhakrishnan, V.B., Chakraborty, A.: Text-based person search via attribute-aided matching[C]\/\/Proceedings of the IEEE\/CVF winter conference on applications of computer vision: 2617\u20132625 (2020)","DOI":"10.1109\/WACV45572.2020.9093640"},{"key":"4213_CR19","doi-asserted-by":"publisher","first-page":"7699","DOI":"10.1109\/TMM.2022.3225754","volume":"25","author":"Z Ji","year":"2022","unstructured":"Ji, Z., Hu, J., Liu, D., Wu, L.Y., Zhao, Y.: Asymmetric cross-scale alignment for text-based person search. IEEE Trans. Multimedia 25, 7699\u20137709 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"4213_CR20","doi-asserted-by":"crossref","unstructured":"Zuo, J., Zhou, H., Nie, Y., et al.: UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity, Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 22010\u201322019 (2024)","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"4213_CR21","unstructured":"Devlin, J., Chang, M. W., Lee, K., et al.: Bert: Pre-training of deep bidirectional transformers for language understanding[C]\/\/Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers).: 4171\u20134186 (2019)"},{"key":"4213_CR22","doi-asserted-by":"crossref","unstructured":"Cao, M., Bai, Y., Zeng, Z., et al.: An empirical study of clip for text-based person search[C]\/\/Proceedings of the AAAI Conference on Artificial Intelligence. 38(1): 465\u2013473 (2024)","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"4213_CR23","doi-asserted-by":"crossref","unstructured":"Wu, Z., Ma, S.: CLIP-Based Multi-level Alignment for Text-based Person Search[C]\/\/2024 5th International Conference on Computer Engineering and Application (ICCEA). IEEE: 610\u2013614 (2024)","DOI":"10.1109\/ICCEA62105.2024.10603861"},{"key":"4213_CR24","doi-asserted-by":"crossref","unstructured":"Tian, Y., Li, Y., Wang, D., et al.: Enhancing CLIP-Based Text-Person Retrieval by Leveraging Negative Samples[C]\/\/Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Singapore: Springer Nature Singapore, 271\u2013283 (2023)","DOI":"10.1007\/978-981-99-8540-1_22"},{"issue":"1","key":"4213_CR25","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s00371-023-02769-2","volume":"40","author":"Jize Zhang","year":"2024","unstructured":"Zhang, Jize, et al.: Invertible network for unpaired low-light image enhancement. The Visual Computer 40(1), 109\u2013120 (2024)","journal-title":"The Visual Computer"},{"issue":"1","key":"4213_CR26","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/s00371-023-02770-9","volume":"40","author":"Kavinder Singh","year":"2024","unstructured":"Singh, Kavinder, Parihar, Anil Singh: Illumination estimation for nature preserving low-light image enhancement. The Visual Computer 40(1), 121\u2013136 (2024)","journal-title":"The Visual Computer"},{"issue":"6","key":"4213_CR27","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1016\/j.vrih.2023.06.003","volume":"5","author":"MingKang Wang","year":"2023","unstructured":"Wang, MingKang, et al.: Adequate alignment and interaction for cross-modal retrieval. Virtual Reality and Intelligent Hardware 5(6), 509\u2013522 (2023)","journal-title":"Virtual Reality and Intelligent Hardware"},{"key":"4213_CR28","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":"4213_CR29","doi-asserted-by":"crossref","unstructured":"Liu, J., Zha, Z. J., Hong, R., et al.: Deep adversarial graph attention convolution network for text-based person search[C]\/\/Proceedings of the 27th ACM international conference on multimedia. 665\u2013673 (2019)","DOI":"10.1145\/3343031.3350991"},{"key":"4213_CR30","doi-asserted-by":"crossref","unstructured":"Wang, C., Luo, Z., Lin, Y., et al.: Text-based person search via multi-granularity embedding learning[C]\/\/IJCAI. 1068\u20131074 (2021)","DOI":"10.24963\/ijcai.2021\/148"},{"key":"4213_CR31","doi-asserted-by":"crossref","unstructured":"Zheng, K., Liu, W., Liu, J., et al.: Hierarchical gumbel attention network for text-based person search[C]\/\/Proceedings of the 28th ACM international conference on multimedia. 3441\u20133449 (2020)","DOI":"10.1145\/3394171.3413864"},{"key":"4213_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, H.: \u201cDeep cross-modal projection learning for image-text matching,\u201d in Proceedings of the European Conference on Computer Vision (ECCV), pp. 686\u2013701 (2018)","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"4213_CR33","doi-asserted-by":"publisher","first-page":"2226","DOI":"10.1109\/TMM.2022.3144890","volume":"25","author":"Nan Jiang","year":"2022","unstructured":"Jiang, Nan, et al.: Photohelper: portrait photographing guidance via deep feature retrieval and fusion. IEEE Transactions on Multimedia 25, 2226\u20132238 (2022)","journal-title":"IEEE Transactions on Multimedia"},{"issue":"4","key":"4213_CR34","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2287","volume":"35","author":"Jiannan Ye","year":"2024","unstructured":"Ye, Jiannan, et al.: Neural foveated super?resolution for real?time VR rendering. Computer Animation and Virtual Worlds 35(4), e2287 (2024)","journal-title":"Computer Animation and Virtual Worlds"},{"key":"4213_CR35","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization[C]\/\/Proceedings of the IEEE international conference on computer vision. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"4213_CR36","doi-asserted-by":"crossref","unstructured":"Cao, M., Bai, Y., Zeng, Z., et al.: An empirical study of clip for text-based person search[C]\/\/Proceedings of the AAAI Conference on Artificial Intelligence. , 38(1): 465\u2013473 (2024)","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"4213_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Y., Qin, G., Chen, H., et al.: Causality-inspired invariant representation learning for text-based person retrieval[C]\/\/Proceedings of the AAAI Conference on Artificial Intelligence. 38(12): 14052\u201314060 (2024)","DOI":"10.1609\/aaai.v38i12.29314"},{"key":"4213_CR38","doi-asserted-by":"crossref","unstructured":"Qin, Y., Chen, Y., Peng, D., et al.: Noisy-correspondence learning for text-to-image person re-identification[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 27197\u201327206 (2024)","DOI":"10.1109\/CVPR52733.2024.02568"},{"issue":"2","key":"4213_CR39","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 embed- dings with instance loss. ACM Transactions on Multi- media Computing, Communications, and Applications (TOMM) 16(2), 1\u201323 (2020)","journal-title":"ACM Transactions on Multi- media Computing, Communications, and Applications (TOMM)"},{"key":"4213_CR40","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching, in Proceed- ings of the European Conference on Computer Vision (ECCV), pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04213-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04213-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04213-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T13:05:09Z","timestamp":1772629509000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04213-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["4213"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04213-z","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7010785\/v1","asserted-by":"object"}]},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,12]]},"assertion":[{"value":"30 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"45"}}