{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T13:10:08Z","timestamp":1748092208810,"version":"3.41.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915680","type":"print"},{"value":"9783031915697","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91569-7_19","type":"book-chapter","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:49:35Z","timestamp":1748090975000},"page":"303-319","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fashion Attribute Extraction Under an\u00a0Evolving Ontology"],"prefix":"10.1007","author":[{"given":"Aditya","family":"Kanade","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manasi","family":"Patwardhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mayur","family":"Patidar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lovekesh","family":"Vig","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bagyalakshmi","family":"Vasudevan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Arslan, H.S., Sirts, K., Fishel, M., Anbarjafari, G.: Multimodal sequential fashion attribute prediction. Information 10, 308 (2019). https:\/\/api.semanticscholar.org\/CorpusID:208106486","DOI":"10.3390\/info10100308"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Azizi, Z., Kuo, C.C.J.: Pager: progressive attribute-guided extendable robust image generation. arXiv:2206.00162 (2022). https:\/\/api.semanticscholar.org\/CorpusID:249240623","DOI":"10.1561\/116.00000034"},{"key":"19_CR3","unstructured":"Chia, P.J., et al.: Fashionclip: connecting language and images for product representations. arXiv:2204.03972 (2022). https:\/\/api.semanticscholar.org\/CorpusID:248069345"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Cho, H., Ahn, C., Yoo, K.M., Seol, J., goo Lee, S.: Leveraging class hierarchy in fashion classification. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 3197\u20133200 (2019). https:\/\/api.semanticscholar.org\/CorpusID:207894438","DOI":"10.1109\/ICCVW.2019.00398"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Divitiis, L.D., Becattini, F., Baecchi, C., Bimbo, A.: Disentangling features for fashion recommendation. ACM Trans. Multimedia Comput. Commun. Appl. 19, 1 \u2013 21 (2022). https:\/\/api.semanticscholar.org\/CorpusID:248243754","DOI":"10.1145\/3531017"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Fine-grained fashion similarity prediction by attribute-specific embedding learning. IEEE Trans. Image Process. 30, 8410\u20138425 (2021). https:\/\/api.semanticscholar.org\/CorpusID:233033610","DOI":"10.1109\/TIP.2021.3115658"},{"key":"19_CR7","unstructured":"Garg, S., et al.: Tic-clip: continual training of clip models. arXiv:abs\/2310.16226 (2023). https:\/\/api.semanticscholar.org\/CorpusID:264487212"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Fashionpedia: ontology, segmentation, and an attribute localization dataset. In: European Conference on Computer Vision (2020). https:\/\/api.semanticscholar.org\/CorpusID:216553612","DOI":"10.1007\/978-3-030-58452-8_19"},{"key":"19_CR9","doi-asserted-by":"publisher","unstructured":"Jia, Q., et al.: KG-FLIP: knowledge-guided fashion-domain language-image pre-training for E-commerce. In: Sitaram, S., Beigman\u00a0Klebanov, B., Williams, J.D. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pp. 81\u201388. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-industry.9, https:\/\/aclanthology.org\/2023.acl-industry.9","DOI":"10.18653\/v1\/2023.acl-industry.9"},{"key":"19_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2014). https:\/\/api.semanticscholar.org\/CorpusID:6628106"},{"key":"19_CR11","unstructured":"Koh, J.Y., Salakhutdinov, R., Fried, D.: Grounding language models to images for multimodal inputs and outputs. In: International Conference on Machine Learning (2023). https:\/\/api.semanticscholar.org\/CorpusID:258947258"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Kolisnik, B., Hogan, I., Zulkernine, F.H.: Condition-CNN: a hierarchical multi-label fashion image classification model. Expert Syst. Appl. 182, 115195 (2021). https:\/\/api.semanticscholar.org\/CorpusID:236238421","DOI":"10.1016\/j.eswa.2021.115195"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Lee, K.Y., Zhong, Y., Wang, Y.X.: Do pre-trained models benefit equally in continual learning? In: 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 6474\u20136482 (2022). https:\/\/api.semanticscholar.org\/CorpusID:253223819","DOI":"10.1109\/WACV56688.2023.00642"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Li, P., Li, Y., Jiang, X., Zhen, X.: Two-stream multi-task network for fashion recognition. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 3038\u20133042 (2019). https:\/\/api.semanticscholar.org\/CorpusID:59336329","DOI":"10.1109\/ICIP.2019.8803394"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40, 2935\u20132947 (2016). https:\/\/api.semanticscholar.org\/CorpusID:4853851","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Liao, L., He, X., Zhao, B., Ngo, C.W., Chua, T.S.: Interpretable multimodal retrieval for fashion products. In: Proceedings of the 26th ACM international conference on Multimedia (2018) https:\/\/api.semanticscholar.org\/CorpusID:53036667","DOI":"10.1145\/3240508.3240646"},{"key":"19_CR17","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 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"19_CR18","unstructured":"Merullo, J., Castricato, L., Eickhoff, C., Pavlick, E.: Linearly mapping from image to text space. arXiv:2209.15162 (2022). https:\/\/api.semanticscholar.org\/CorpusID:252668479"},{"key":"19_CR19","unstructured":"Ni, Z., Wei, L., Tang, S., Zhuang, Y., Tian, Q.: Continual vision-language representation learning with off-diagonal information. In: International Conference on Machine Learning (2023). https:\/\/api.semanticscholar.org\/CorpusID:258676581"},{"key":"19_CR20","unstructured":"Paliwal, S., et al.: Ontology guided supervised contrastive learning for fine-grained attribute extraction from fashion images. In: eCom@SIGIR (2023). https:\/\/api.semanticscholar.org\/CorpusID:266598601"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Papadopoulos, S., et al.: Attentive hierarchical label sharing for enhanced garment and attribute classification of fashion imagery (2021). https:\/\/api.semanticscholar.org\/CorpusID:245747013","DOI":"10.1007\/978-3-030-94016-4_7"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Parekh, V., Shaik, K., Biswas, S., Chelliah, M.: Fine-grained visual attribute extraction from fashion wear. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 3968\u20133972 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235679931","DOI":"10.1109\/CVPRW53098.2021.00447"},{"key":"19_CR23","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021). https:\/\/api.semanticscholar.org\/CorpusID:231591445"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Shajini, M., Ramanan, A.: Multi-staged feature-attentive network for fashion clothing classification and attribute prediction. In: ELCVIA Electronic Letters on Computer Vision and Image Analysis (2022). https:\/\/api.semanticscholar.org\/CorpusID:246582485","DOI":"10.5565\/rev\/elcvia.1409"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Shin, M.: Semi-supervised learning with a teacher-student network for generalized attribute prediction. In: European Conference on Computer Vision (2020). https:\/\/api.semanticscholar.org\/CorpusID:220514779","DOI":"10.1007\/978-3-030-58621-8_30"},{"key":"19_CR26","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arxiv:2312.11805 (2024)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Yan, C., Yan, K., Zhang, Y., Wan, Y., Zhu, D.: Attribute-guided fashion image retrieval by iterative similarity learning. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136 (2022). https:\/\/api.semanticscholar.org\/CorpusID:251847943","DOI":"10.1109\/ICME52920.2022.9859953"},{"key":"19_CR28","unstructured":"Zhang, S., et al.: Opt: open pre-trained transformer language models. ArXiv abs\/2205.01068 (2022). https:\/\/api.semanticscholar.org\/CorpusID:248496292"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Ma, M., Wang, K., Qin, Z., Yue, X., You, Y.: Preventing zero-shot transfer degradation in continual learning of vision-language models. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 19068\u201319079 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257496481","DOI":"10.1109\/ICCV51070.2023.01752"},{"key":"19_CR30","unstructured":"Zhou, D.W., Wang, Q., Qi, Z., Ye, H.J., chuan Zhan, D., Liu, Z.: Deep class-incremental learning: a survey. arXiv:2302.03648 (2023). https:\/\/api.semanticscholar.org\/CorpusID:256627357"},{"key":"19_CR31","unstructured":"Zhou, D.W., Zhang, Y., Ning, J., Ye, H.J., Zhan, D.C., Liu, Z.: Learning without forgetting for vision-language models (2023)"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Zou, H.P., et al.: Eiven: efficient implicit attribute value extraction using multimodal LLM (2024)","DOI":"10.18653\/v1\/2024.naacl-industry.40"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Zou, X., Kong, X., Wong, W.K., Wang, C., Liu, Y., Cao, Y.: Fashionai: a hierarchical dataset for fashion understanding. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 296\u2013304 (2019). https:\/\/api.semanticscholar.org\/CorpusID:202784769","DOI":"10.1109\/CVPRW.2019.00039"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91569-7_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:49:44Z","timestamp":1748090984000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91569-7_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915680","9783031915697"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91569-7_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}