{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T13:46:43Z","timestamp":1793713603294,"version":"4.6.1"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376137, 62276155, 62376140,U23A20315"],"award-info":[{"award-number":["62376137, 62276155, 62376140,U23A20315"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shandong Provincial Natural Science Foundation","award":["ZR2022YQ59, ZR2021MF040"],"award-info":[{"award-number":["ZR2022YQ59, ZR2021MF040"]}]},{"name":"Science and Technology Innovation Program for Distinguished Young Scholars of Shandong Province Higher Education Institutions","award":["2023KJ128"],"award-info":[{"award-number":["2023KJ128"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657831","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"240-250","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":36,"title":["Fine-grained Textual Inversion Network for Zero-Shot Composed Image Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5768-5467","authenticated-orcid":false,"given":"Haoqiang","family":"Lin","sequence":"first","affiliation":[{"name":"Shandong University, Qingdao, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0633-3722","authenticated-orcid":false,"given":"Haokun","family":"Wen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5274-4197","authenticated-orcid":false,"given":"Xuemeng","family":"Song","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1582-5764","authenticated-orcid":false,"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong Jianzhu University, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5653-8286","authenticated-orcid":false,"given":"Yupeng","family":"Hu","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR","author":"Cho Jaemin","year":"2021","unstructured":"Jaemin Cho, Jie Lei, Hao Tan, and Mohit Bansal. 2021. Unifying Vision-and-Language Tasks via Text Generation. In Proceedings of the International Conference on Machine Learning. PMLR, 1931--1942."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/192593.192658"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_32"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--12","author":"Delmas Ginger","year":"2022","unstructured":"Ginger Delmas, Rafael S. Rezende, Gabriela Csurka, and Diane Larlus. 2022. ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity. In Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--12."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--18","author":"Gal Rinon","year":"2023","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit Haim Bermano, Gal Chechik, and Daniel Cohen-or. 2023. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. In Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--18."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475619"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00262"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00067"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In Proceedings of the International Conference on Machine Learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_22_1","first-page":"9694","article-title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","volume":"34","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. Advances in Neural Information Processing Systems 34 (2021), 9694--9705.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the Australasian Joint Conference on Artificial Intelligence. Springer, 190--202","author":"Lin Haoqiang","year":"2023","unstructured":"Haoqiang Lin, HaokunWen, Xiaolin Chen, and Xuemeng Song. 2023. CLIP-based Composed Image Retrieval with Comprehensive Fusion and Data Augmentation. In Proceedings of the Australasian Joint Conference on Artificial Intelligence. Springer, 190--202."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531776"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--11","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--11."},{"key":"e_1_3_2_1_28_1","first-page":"8024","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","volume":"32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. Advances in Neural Information Processing Systems 32 (2019), 8024--8035.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2727--2737","author":"Rao Jun","year":"2022","unstructured":"Jun Rao, Fei Wang, Liang Ding, Shuhan Qi, Yibing Zhan, Weifeng Liu, and Dacheng Tao. 2022. Where Does the Performance Improvement Come From? - A Reproducibility Concern about Image-Text Retrieval. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2727--2737."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"e_1_3_2_1_36_1","first-page":"5998","article-title":"Attention Is All You Need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. Advances in Neural Information Processing Systems 30 (2017), 5998--6008.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--14","author":"Wang Zirui","year":"2022","unstructured":"Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, and Yuan Cao. 2022. SimVLM: Simple Visual Language Model Pretraining with Weak Supervision. In Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--14."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462967"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3346434"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611817"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462881"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532047"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657831","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:39:17Z","timestamp":1755841157000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":45,"alternative-id":["10.1145\/3626772.3657831","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657831","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}