{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:27:22Z","timestamp":1791304042149,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222212, 62336001"],"award-info":[{"award-number":["62222212, 62336001"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Artificial Intelligence-National Science and Technology Major Project","award":["2023ZD0121200"],"award-info":[{"award-number":["2023ZD0121200"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730074","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:18:36Z","timestamp":1752455916000},"page":"833-843","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Rethinking Pseudo Word Learning in Zero-Shot Composed Image Retrieval: From an Object-Aware Perspective"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4716-614X","authenticated-orcid":false,"given":"Zhe","family":"Li","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2839-8693","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2140-2546","authenticated-orcid":false,"given":"Kun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Suzhou Institute for Advance Research, USTC, Suzhou, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2774-2875","authenticated-orcid":false,"given":"Weidong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_5_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Chen Yiyang","year":"2024","unstructured":"Yiyang Chen, Zhedong Zheng, Wei Ji, Leigang Qu, and Tat-Seng Chua. 2024a. Composed image retrieval with text feedback via multi-grained uncertainty regularization. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27885"},{"key":"e_1_3_2_1_7_1","volume-title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity. In International Conference on Learning Representations.","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 International Conference on Learning Representations."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"e_1_3_2_1_10_1","volume-title":"Modality-agnostic attention fusion for visual search with text feedback. arXiv preprint arXiv:2007.00145","author":"Dodds Eric","year":"2020","unstructured":"Eric Dodds, Jack Culpepper, Simao Herdade, Yang Zhang, and Kofi Boakye. 2020. Modality-agnostic attention fusion for visual search with text feedback. arXiv preprint arXiv:2007.00145 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Du Yongchao","year":"2024","unstructured":"Yongchao Du, Min Wang, Wengang Zhou, Shuping Hui, and Houqiang Li. 2024. Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02485"},{"key":"e_1_3_2_1_14_1","volume-title":"Compodiff: Versatile composed image retrieval with latent diffusion. arXiv preprint arXiv:2303.11916","author":"Gu Geonmo","year":"2023","unstructured":"Geonmo Gu, Sanghyuk Chun, Wonjae Kim, HeeJae Jun, Yoohoon Kang, and Sangdoo Yun. 2023. Compodiff: Versatile composed image retrieval with latent diffusion. arXiv preprint arXiv:2303.11916 (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01256"},{"key":"e_1_3_2_1_16_1","volume-title":"Sofie Van Landeghem, and Adriane Boyd","author":"Honnibal Matthew","year":"2020","unstructured":"Matthew Honnibal, Ines Montani, Sofie Van Landeghem, and Adriane Boyd. 2020. Industrial-strength natural language processing in python. spaCy (2020)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00067"},{"key":"e_1_3_2_1_18_1","volume-title":"European Conference on Computer Vision. Springer, 239-254","author":"Jang Young Kyun","year":"2024","unstructured":"Young Kyun Jang, Dat Huynh, Ashish Shah, Wen-Kai Chen, and Ser-Nam Lim. 2024. Spherical linear interpolation and text-anchoring for zero-shot composed image retrieval. In European Conference on Computer Vision. Springer, 239-254."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/100216.100262"},{"key":"e_1_3_2_1_20_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Karthik Shyamgopal","year":"2024","unstructured":"Shyamgopal Karthik, Karsten Roth, Massimiliano Mancini, and Zeynep Akata. 2024. Vision-by-language for training-free compositional image retrieval. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28081"},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_25_1","volume-title":"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 International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358411"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369656"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657831"},{"key":"e_1_3_2_1_29_1","first-page":"740","volume-title":"Zurich","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740-755."},{"key":"e_1_3_2_1_30_1","volume-title":"The 34th British Machine Vision Conference (BMVC","author":"Liu Yikun","year":"2023","unstructured":"Yikun Liu, Jiangchao Yao, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2023. Zero-shot composed text-image retrieval. In The 34th British Machine Vision Conference (BMVC 2023). BMVA."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"e_1_3_2_1_33_1","volume-title":"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 International conference on machine learning. PMLR, 8748-8763."},{"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\/P18-1238"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"e_1_3_2_1_37_1","volume-title":"Rtic: Residual learning for text and image composition using graph convolutional network. arXiv preprint arXiv:2104.03015","author":"Shin Minchul","year":"2021","unstructured":"Minchul Shin, Yoonjae Cho, Byungsoo Ko, and Geonmo Gu. 2021. Rtic: Residual learning for text and image composition using graph convolutional network. arXiv preprint arXiv:2104.03015 (2021)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02545"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28324"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449963"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657727"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462967"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611817"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_2_1_46_1","volume-title":"Sentence-level Prompts Benefit Composed Image Retrieval. In The Twelfth International Conference on Learning Representations.","author":"Xu Xinxing","year":"2024","unstructured":"Xinxing Xu, Yong Liu, Salman Khan, Fahad Khan, Wangmeng Zuo, Rick Siow Mong Goh, Chun-Mei Feng, et al., 2024. Sentence-level Prompts Benefit Composed Image Retrieval. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3299791"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28479"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657740"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611703"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:34:27Z","timestamp":1755887667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730074"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":52,"alternative-id":["10.1145\/3726302.3730074","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730074","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}