{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T13:29:52Z","timestamp":1742995792418,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819756742"},{"type":"electronic","value":"9789819756759"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5675-9_38","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T01:10:40Z","timestamp":1722474640000},"page":"447-459","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SHAF: Semantic-Guided Hierarchical Alignment and Fusion for Composed Image Retrieval"],"prefix":"10.1007","author":[{"given":"Cairong","family":"Yan","sequence":"first","affiliation":[]},{"given":"Erhe","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Ran","family":"Tao","sequence":"additional","affiliation":[]},{"given":"Yongquan","family":"Wan","sequence":"additional","affiliation":[]},{"given":"Derun","family":"Ai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","unstructured":"Tian, Y., Newsam, S., Boakye, K.: Fashion image retrieval with text feedback by additive attention compositional learning. In: WACV, pp. 1011\u20131021 (2023)","DOI":"10.1109\/WACV56688.2023.00107"},{"key":"38_CR2","unstructured":"Zhang, X., Zheng, Z., Wang, X., Yang, Y.: Relieving triplet ambiguity: consensus network for language-guided image retrieval. arXiv preprint arXiv:2306.02092 (2023)"},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Levy, M., Ben-Ari, R., Darshan, N., Lischinski, D.: Data roaming and early fusion for composed image retrieval. arXiv preprint arXiv:2303.09429 (2023)","DOI":"10.1609\/aaai.v38i4.28081"},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Baldrati, A., Bertini, M., Uricchio, T., Del Bimbo, A.: Conditioned and composed image retrieval combining and partially fine-tuning CLIP-based features. In: CVPR, pp. 4955\u20134964 (2022)","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Wu, H., Gao, Y., Guo, X., Al-Halah, Z., Rennie, S.: Fashion IQ: a new dataset towards retrieving images by natural language feedback. In: CVPR, pp. 11302\u201311312 (2021)","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"38_CR6","unstructured":"Delmas, G., Rezende, R., Csurka, G., Larlus, D.: ARTEMIS: attention-based retrieval with text-explicit matching and implicit similarity. In: ICLR (2022)"},{"issue":"1","key":"38_CR7","doi-asserted-by":"publisher","first-page":"18958","DOI":"10.1038\/s41598-022-23052-9","volume":"12","author":"P Chia","year":"2022","unstructured":"Chia, P., Attanasio, G., Bianchi, F., Terragni, S.: Contrastive language and vision learning of general fashion concepts. Sci. Rep. 12(1), 18958 (2022)","journal-title":"Sci. Rep."},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Goenka, S., Zheng, Z., Jaiswal, A., Chada, R.: FashionVLP: vision language transformer for fashion retrieval with feedback. In: CVPR, pp. 14085\u201314095 (2022)","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR, pp. 16795\u201316804 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Kim, J., Yu, Y., Kim, H., Kim, G.: Dual compositional learning in interactive image retrieval. In: AAAI, pp. 1771\u20131779 (2021)","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Wen, H., Song, X., Yang, X., Zhan, Y., Nie, L.: Comprehensive linguistic-visual composition network for image retrieval. In: SIGIR, pp. 1369\u20131378 (2021)","DOI":"10.1145\/3404835.3462967"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"M. U. Anwaar, E. Labintcev, and M. Kleinsteuber, \u201cCompositional learning of image-text query for image retrieval,\u201d in WACV, 2021, pp. 1139\u20131148","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"38_CR13","unstructured":"Chen, Y., Zheng, Z., Ji, W., Qu, L., Chua, T.-S.: Composed image retrieval with text feedback via multi-grained uncertainty regularization. In: ICLR (2024)"},{"key":"38_CR14","unstructured":"Shin, M., Cho, Y., Ko, B., Gu, G.: RTIC: residual learning for text and image composition using graph convolutional network. arXiv preprint arXiv:2104.03015 (2021)"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Rodriguez-Opazo, C., Teney, D., Gould, S.: Image retrieval on real-life images with re-trained vision-and-language models. In: CVPR, pp. 2105\u20132114 (2021)","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"Lee, S., Kim, D., Han, B.: Cosmo: content-style modulation for image retrieval with text feedback. In: CVPR, pp. 802\u2013812 (2021)","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"38_CR17","unstructured":"Radford, A., Hallacy, C., Ramesh, A., Goh, G.: Learning transferable visual models from natural language supervision. In: PMLR, pp. 8748\u20138763 (2021)"},{"key":"38_CR18","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M.: Language models are few-shot learners. NIPS 33, 1877\u20131901 (2020)","journal-title":"NIPS"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Chen, Y., Gong, S., Bazzani, L.: Image search with text feedback by visiolinguistic attention learning. In: CVPR, pp. 2998\u20133008 (2020)","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"38_CR20","unstructured":"Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Berg, T.L., Berg, A.C., Shih, J.: Automatic attribute discovery and characterization from noisy web data. In: ECCV, pp. 663\u2013676 (2010)","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"38_CR22","doi-asserted-by":"crossref","unstructured":"Vo, N., Jiang, L., Sun, C., Murphy, K.: Composing text and image for image retrieval-an empirical odyssey. In: CVPR, pp. 6439\u20136448 (2019)","DOI":"10.1109\/CVPR.2019.00660"},{"key":"38_CR23","first-page":"5998","volume":"33","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Guyon, I., Luxburg, U.V., Bengio, S.: Attention is all you need. NIPS 33, 5998\u20136008 (2017)","journal-title":"NIPS"},{"key":"38_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, H., Wei, Y., Zhao, Y., Zhang, C., Huang, S.: AMC: adaptive multi-expert collaborative network for text-guided image retrieval. ACM Trans. Multim. Comput. Commun. Appl. (2023)","DOI":"10.1145\/3584703"},{"key":"38_CR25","unstructured":"Wang, Z., Codella, N., Chen, Y.: CLIP-TD: CLIP targeted distillation for vision-language tasks. arXiv preprint arXiv:2201.05729 (2022)"},{"key":"38_CR26","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y.: DocFormer: end-to-end transformer for document understanding. In: ICCV, pp. 973\u2013983 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5675-9_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T01:21:49Z","timestamp":1722475309000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5675-9_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756742","9789819756759"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5675-9_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}