{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:22:30Z","timestamp":1775665350213,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"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_24","type":"book-chapter","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:50:17Z","timestamp":1748091017000},"page":"385-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Garment Attribute Manipulation with\u00a0Multi-level Attention"],"prefix":"10.1007","author":[{"given":"Vittorio","family":"Casula","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6131-1505","authenticated-orcid":false,"given":"Lorenzo","family":"Berlincioni","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2483-9927","authenticated-orcid":false,"given":"Luca","family":"Cultrera","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2537-2700","authenticated-orcid":false,"given":"Federico","family":"Becattini","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5517-2198","authenticated-orcid":false,"given":"Chiara","family":"Pero","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1358-006X","authenticated-orcid":false,"given":"Carmen","family":"Bisogni","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1364-218X","authenticated-orcid":false,"given":"Marco","family":"Bertini","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1052-8322","authenticated-orcid":false,"given":"Alberto Del","family":"Bimbo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"issue":"11","key":"24_CR1","doi-asserted-by":"publisher","first-page":"1949","DOI":"10.1109\/TMM.2015.2477680","volume":"17","author":"AH Abdulnabi","year":"2015","unstructured":"Abdulnabi, A.H., Wang, G., Lu, J., Jia, K.: Multi-task CNN model for attribute prediction. IEEE Trans. Multimedia 17(11), 1949\u20131959 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Ak, K.E., Kassim, A.A., Lim, J.H., Tham, J.Y.: Learning attribute representations with localization for flexible fashion search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7708\u20137717 (2018)","DOI":"10.1109\/CVPR.2018.00804"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Ak, K.E., Lim, J.H., Tham, J.Y., Kassim, A.A.: Efficient multi-attribute similarity learning towards attribute-based fashion search. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1671\u20131679. IEEE (2018)","DOI":"10.1109\/WACV.2018.00186"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Ak, K.E., Lim, J.H., Tham, J.Y., Kassim, A.A.: Attribute manipulation generative adversarial networks for fashion images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10541\u201310550 (2019)","DOI":"10.1109\/ICCV.2019.01064"},{"key":"24_CR5","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Baldrati, A., Morelli, D., Cartella, G., Cornia, M., Bertini, M., Cucchiara, R.: Multimodal garment designer: human-centric latent diffusion models for fashion image editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23393\u201323402 (2023)","DOI":"10.1109\/ICCV51070.2023.02138"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Baldrati, A., Morelli, D., Cornia, M., Bertini, M., Cucchiara, R.: Multimodal-conditioned latent diffusion models for fashion image editing. arXiv preprint arXiv:2403.14828 (2024)","DOI":"10.1109\/ICCV51070.2023.02138"},{"issue":"24","key":"24_CR8","doi-asserted-by":"publisher","first-page":"38217","DOI":"10.1007\/s11042-023-15290-4","volume":"82","author":"F Becattini","year":"2023","unstructured":"Becattini, F., De Divitiis, L., Baecchi, C., Bimbo, A.D.: Fashion recommendation based on style and social events. Multimedia Tools Appl. 82(24), 38217\u201338232 (2023)","journal-title":"Multimedia Tools Appl."},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Becattini, F., et al: PLM-IPE: a pixel-landmark mutual enhanced framework for implicit preference estimation. In: Proceedings of the 3rd ACM International Conference on Multimedia in Asia, pp.\u00a01\u20135 (2021)","DOI":"10.1145\/3469877.3490621"},{"issue":"1","key":"24_CR10","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1109\/TETC.2023.3268363","volume":"12","author":"F Becattini","year":"2023","unstructured":"Becattini, F., Teotini, F.M., Del Bimbo, A.: Transformer-based graph neural networks for outfit generation. IEEE Trans. Emerg. Top. Comput. 12(1), 213\u2013223 (2023)","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Bhattacharya, G., Kilari, N., Gubbi, J., Pal, A., et\u00a0al.: DatrNet: disentangling fashion attribute embedding for substitute item retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2283\u20132287 (2022)","DOI":"10.1109\/CVPRW56347.2022.00253"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., Fan, Q., Panda, R.: CrossVit: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"24_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-030-68790-8_23","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"L De Divitiis","year":"2021","unstructured":"De Divitiis, L., Becattini, F., Baecchi, C., Del Bimbo, A.: Garment recommendation with memory augmented neural networks. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12662, pp. 282\u2013295. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68790-8_23"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"De\u00a0Divitiis, L., Becattini, F., Baecchi, C., Del\u00a0Bimbo, A.: Style-based outfit recommendation. In: 2021 International Conference on Content-Based Multimedia Indexing (CBMI), pp.\u00a01\u20134. IEEE (2021)","DOI":"10.1109\/CBMI50038.2021.9461912"},{"issue":"1s","key":"24_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3531017","volume":"19","author":"L De Divitiis","year":"2023","unstructured":"De Divitiis, L., Becattini, F., Baecchi, C., Del Bimbo, A.: Disentangling features for fashion recommendation. ACM Trans. Multimed. Comput. Commun. Appl. 19(1s), 1\u201321 (2023)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"24_CR16","unstructured":"Douze, M., et al.: The faiss library (2024)"},{"issue":"5","key":"24_CR17","doi-asserted-by":"publisher","first-page":"2687","DOI":"10.1109\/TCSVT.2021.3080920","volume":"32","author":"SR Dubey","year":"2022","unstructured":"Dubey, S.R.: A decade survey of content based image retrieval using deep learning. IEEE Trans. Circuits Syst. Video Technol. 32(5), 2687\u20132704 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2021.3080920","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Ge, Y., Zhang, R., Wang, X., Tang, X., Luo, P.: DeepFashion2: a versatile benchmark for detection, pose estimation, segmentation and re-identification of clothing images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5337\u20135345 (2019)","DOI":"10.1109\/CVPR.2019.00548"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Han, X., Wu, Z., Jiang, Y.G., Davis, L.S.: Learning fashion compatibility with bidirectional LSTMS. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1078\u20131086 (2017)","DOI":"10.1145\/3123266.3123394"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Han, X., Wu, Z., Wu, Z., Yu, R., Davis, L.S.: Viton: an image-based virtual try-on network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7543\u20137552 (2018)","DOI":"10.1109\/CVPR.2018.00787"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Hou, Y., Vig, E., Donoser, M., Bazzani, L.: Learning attribute-driven disentangled representations for interactive fashion retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12147\u201312157 (2021)","DOI":"10.1109\/ICCV48922.2021.01193"},{"key":"24_CR22","doi-asserted-by":"publisher","unstructured":"Islam, S.M., Joardar, S., Sekh*, A.A.: A survey on fashion image retrieval. ACM Comput. Surv. 56(6) (2024). https:\/\/doi.org\/10.1145\/3636552","DOI":"10.1145\/3636552"},{"issue":"4","key":"24_CR23","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/582415.582418","volume":"20","author":"K J\u00e4rvelin","year":"2002","unstructured":"J\u00e4rvelin, K., Kek\u00e4l\u00e4inen, J.: Cumulated gain-based evaluation of IR techniques. ACM Trans. Inf. Syst. (TOIS) 20(4), 422\u2013446 (2002)","journal-title":"ACM Trans. Inf. Syst. (TOIS)"},{"key":"24_CR24","doi-asserted-by":"publisher","unstructured":"Jiao, Y., Xie, N., Gao, Y., Wang, C.C., Sun, Y.: Fine-grained fashion representation learning by online deep clustering. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision. pp. 19\u201335. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_2","DOI":"10.1007\/978-3-031-19812-0_2"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Kovashka, A., Parikh, D., Grauman, K.: WhittleSearch: image search with relative attribute feedback. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2973\u20132980. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248026"},{"key":"24_CR26","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol.\u00a025. Curran Associates, Inc. (2012). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2012\/file\/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, J., Wang, J., Liu, Z.: MMFashion: an open-source toolbox for visual fashion analysis. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3755\u20133758 (2021)","DOI":"10.1145\/3474085.3478327"},{"key":"24_CR28","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":"24_CR29","doi-asserted-by":"crossref","unstructured":"Ma, Z., et al.: Fine-grained fashion similarity learning by attribute-specific embedding network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11741\u201311748 (2020)","DOI":"10.1609\/aaai.v34i07.6845"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Morelli, D., Fincato, M., Cornia, M., Landi, F., Cesari, F., Cucchiara, R.: Dress code: high-resolution multi-category virtual try-on. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2231\u20132235 (2022)","DOI":"10.1109\/CVPRW56347.2022.00243"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Park, S., Shin, M., Ham, S., Choe, S., Kang, Y.: Study on fashion image retrieval methods for efficient fashion visual search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.\u00a00\u20130 (2019)","DOI":"10.1109\/CVPRW.2019.00042"},{"key":"24_CR32","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.patrec.2023.06.018","volume":"172","author":"G Scaramuzzino","year":"2023","unstructured":"Scaramuzzino, G., Becattini, F., Del Bimbo, A.: Attribute disentanglement with gradient reversal for interactive fashion retrieval. Pattern Recogn. Lett. 172, 203\u2013212 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Song, X., Han, X., Li, Y., Chen, J., Xu, X.S., Nie, L.: GP-BPR: personalized compatibility modeling for clothing matching. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 320\u2013328 (2019)","DOI":"10.1145\/3343031.3350956"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Vaswani, A., Ramachandran, P., Srinivas, A., Parmar, N., Hechtman, B., Shlens, J.: Scaling local self-attention for parameter efficient visual backbones. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12894\u201312904 (2021)","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Fashion IQ: a new dataset towards retrieving images by natural language feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11307\u201311317 (2021)","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Xiao, L., Yamasaki, T.: Attribute-guided multi-level attention network for fine-grained fashion retrieval. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3383785"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, B., Feng, J., Wu, X., Yan, S.: Memory-augmented attribute manipulation networks for interactive fashion search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1520\u20131528 (2017)","DOI":"10.1109\/CVPR.2017.652"},{"key":"24_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/978-3-319-46454-1_36","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J-Y Zhu","year":"2016","unstructured":"Zhu, J.-Y., Kr\u00e4henb\u00fchl, P., Shechtman, E., Efros, A.A.: Generative visual manipulation on the natural image manifold. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 597\u2013613. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_36"}],"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_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:50:24Z","timestamp":1748091024000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91569-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915680","9783031915697"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91569-7_24","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"}}]}}