{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:48:04Z","timestamp":1781585284366,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819770007","type":"print"},{"value":"9789819770014","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T00:00:00Z","timestamp":1726963200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T00:00:00Z","timestamp":1726963200000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-7001-4_21","type":"book-chapter","created":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T18:01:43Z","timestamp":1726941703000},"page":"290-301","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Clothes Image Retrieval via\u00a0Learnable FashionCLIP"],"prefix":"10.1007","author":[{"given":"Yuan","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingbo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,22]]},"reference":[{"key":"21_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/978-3-642-37447-0_25","volume-title":"Computer Vision \u2013 ACCV 2012","author":"L Bossard","year":"2013","unstructured":"Bossard, L., Dantone, M., Leistner, C., Wengert, C., Quack, T., Van Gool, L.: Apparel classification with style. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7727, pp. 321\u2013335. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37447-0_25"},{"key":"21_CR2","unstructured":"Brown, T., et al.: Language models are few-shot learners. arXiv: Computation and Language, arXiv: Computation and Language (2020)"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Q., Huang, J., Feris, R., Brown, L.M., Dong, J., Yan, S.: Deep domain adaptation for describing people based on fine-grained clothing attributes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5315\u20135324 (2015)","DOI":"10.1109\/CVPR.2015.7299169"},{"key":"21_CR4","unstructured":"Chia, P.J., et\u00a0al.: Fashionclip: connecting language and images for product representations (2022)"},{"key":"21_CR5","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North (Jan 2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423, http:\/\/dx.doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"21_CR6","unstructured":"Gao, P., et al.: Clip-adapter: Better vision-language models with feature adapters"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Gu, J., et al.: MSINET: twins contrastive search of multi-scale interaction for object ReID. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19243\u201319253 (2023)","DOI":"10.1109\/CVPR52729.2023.01844"},{"key":"21_CR8","unstructured":"Han, C., et al.: E2vpt: an effective and efficient approach for visual prompt tuning. arXiv preprint arXiv:2307.13770 (2023)"},{"key":"21_CR9","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\/CVF International Conference on Computer Vision, pp. 15013\u201315022 (2021)","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"21_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-319-10590-1_31","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MH Kiapour","year":"2014","unstructured":"Kiapour, M.H., Yamaguchi, K., Berg, A.C., Berg, T.L.: Hipster wars: discovering elements of fashion styles. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 472\u2013488. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_31"},{"key":"21_CR11","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Li, S., Sun, L., Li, Q.: Clip-ReID: exploiting vision-language model for image re-identification without concrete text labels. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1405\u20131413 (2023)","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: Deepfashion: powering robust clothes recognition and retrieval with rich annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1096\u20131104 (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"21_CR14","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\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Ma, R., et al.: Template-free prompt tuning for few-shot NER. arXiv preprint arXiv:2109.13532 (2021)","DOI":"10.18653\/v1\/2022.naacl-main.420"},{"key":"21_CR16","doi-asserted-by":"publisher","unstructured":"Petroni, F., et al.: Language models as knowledge bases? In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019). https:\/\/doi.org\/10.18653\/v1\/d19-1250","DOI":"10.18653\/v1\/d19-1250"},{"key":"21_CR17","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Sun, J., et al.: VPA: fully test-time visual prompt adaptation (2023)","DOI":"10.1145\/3581783.3611835"},{"key":"21_CR19","unstructured":"Tianchi: Watch and buy dataset (2020). https:\/\/tianchi.aliyun.com\/dataset\/75730"},{"key":"21_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Neural Information Processing Systems (2017)"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Wang, H., Shen, J., Liu, Y., Gao, Y., Gavves, E.: NFORMER: robust person re-identification with neighbor transformer (2022)","DOI":"10.1109\/CVPR52688.2022.00715"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: IDPG: an instance-dependent prompt generation method. arXiv preprint arXiv:2204.04497 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.403"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Xie, W., Li, X.H., Cao, C.C., Zhang, N.L.: VIT-CX: causal explanation of vision transformers. arXiv preprint arXiv:2211.03064 (2022)","DOI":"10.24963\/ijcai.2023\/174"},{"key":"21_CR24","unstructured":"Yu, X., Dong, N., Zhu, L., Peng, H., Tao, D.: Clip-driven semantic discovery network for visible-infrared person re-identification (2024)"},{"key":"21_CR25","doi-asserted-by":"publisher","unstructured":"Zhang, E., et al.: One for more: selecting generalizable samples for generalizable ReID model. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3324-3332 (2022). https:\/\/doi.org\/10.1609\/aaai.v35i4.16444","DOI":"10.1609\/aaai.v35i4.16444"},{"key":"21_CR26","doi-asserted-by":"publisher","unstructured":"Zhang, Y., He, B., Sun, L., Li, Q.: Progressive multi-stage feature mix for person re-identification. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2021). https:\/\/doi.org\/10.1109\/icassp39728.2021.9413533","DOI":"10.1109\/icassp39728.2021.9413533"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, J., Lai, S., Chen, X., Wang, D., Lu, H.: Visual prompt multi-modal tracking (2023)","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"21_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1007\/978-3-030-58610-2_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Zhuang","year":"2020","unstructured":"Zhuang, Z., et al.: Rethinking the distribution gap of person re-identification with camera-based batch normalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XII. LNCS, vol. 12357, pp. 140\u2013157. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_9"}],"container-title":["Communications in Computer and Information Science","Neural Computing for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-7001-4_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T18:02:55Z","timestamp":1726941775000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-7001-4_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,22]]},"ISBN":["9789819770007","9789819770014"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-7001-4_21","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,22]]},"assertion":[{"value":"22 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NCAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Computing for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guilin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ncaa2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aaci.org.hk\/ncaa2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}