{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:10:01Z","timestamp":1765008601608,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3770960","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:06:16Z","timestamp":1765008376000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Pseudo-triplet and Flexible Prompt for Zero-shot Composed Image Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1960-5584","authenticated-orcid":false,"given":"Haoyue","family":"Chong","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0834-2075","authenticated-orcid":false,"given":"Lunbo","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4039-7618","authenticated-orcid":false,"given":"Haofeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Lakshita Agarwal and Bindu Verma. 2024. From methods to datasets: A survey on Image-Caption Generators. Multimedia Tools and Applications 83 9 (2024) 28077\u201328123.","DOI":"10.1007\/s11042-023-16560-x"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_43"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"e_1_3_3_2_6_2","first-page":"1597","volume-title":"International conference on machine learning","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597\u20131607."},{"key":"e_1_3_3_2_7_2","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. 2024. Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Ritendra Datta Dhiraj Joshi Jia Li and James\u00a0Z Wang. 2008. Image retrieval: Ideas influences and trends of the new age. ACM Computing Surveys (Csur) 40 2 (2008) 1\u201360.","DOI":"10.1145\/1348246.1348248"},{"key":"e_1_3_3_2_9_2","unstructured":"Lijie Fan Dilip Krishnan Phillip Isola Dina Katabi and Yonglong Tian. 2024. Improving clip training with language rewrites. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612599"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32301"},{"key":"e_1_3_3_2_12_2","unstructured":"Chunjiang Ge Rui Huang Mixue Xie Zihang Lai Shiji Song Shuang Li and Gao Huang. 2023. Domain adaptation via prompt learning. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Geonmo Gu Sanghyuk Chun Wonjae Kim Yoohoon Kang and Sangdoo Yun. 2023. Language-only Efficient Training of Zero-shot Composed Image Retrieval. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023) 13225\u201313234.","DOI":"10.1109\/CVPR52733.2024.01256"},{"key":"e_1_3_3_2_15_2","volume-title":"International Conference on Learning Representations","author":"Hu Edward\u00a0J","year":"2022","unstructured":"Edward\u00a0J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_16_2","first-page":"4904","volume-title":"International conference on machine learning","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904\u20134916."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Yiming Lei Jingqi Li Zilong Li Yuan Cao and Hongming Shan. 2024. Prompt learning in computer vision: a survey. Frontiers of Information Technology & Electronic Engineering 25 1 (2024) 42\u201363.","DOI":"10.1631\/FITEE.2300389"},{"key":"e_1_3_3_2_20_2","first-page":"19730","volume-title":"International conference on machine learning","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\u201319742."},{"key":"e_1_3_3_2_21_2","first-page":"12888","volume-title":"International conference on machine learning","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\u201312900."},{"key":"e_1_3_3_2_22_2","unstructured":"Victor\u00a0Weixin Liang Yuhui Zhang Yongchan Kwon Serena Yeung and James\u00a0Y Zou. 2022. Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning. Advances in Neural Information Processing Systems 35 (2022) 17612\u201317625."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657831"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_3_2_25_2","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong\u00a0Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems 36 (2024)."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"e_1_3_3_2_27_2","volume-title":"International Conference on Learning Representations","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_28_2","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et\u00a0al. 2019. Pytorch: An imperative style high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_2_29_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Andrew Shin Masato Ishii and Takuya Narihira. 2022. Perspectives and prospects on transformer architecture for cross-modal tasks with language and vision. International journal of computer vision 130 2 (2022) 435\u2013454.","DOI":"10.1007\/s11263-021-01547-8"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02545"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28479"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475659"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10648023"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Jingyi Zhang Jiaxing Huang Sheng Jin and Shijian Lu. 2024. Vision-language models for vision tasks: A survey. IEEE transactions on pattern analysis and machine intelligence 46 8 (2024) 5625\u20135644.","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Lei Zhang Shuai Wang and Bing Liu. 2018. Deep learning for sentiment analysis: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 8 4 (2018) e1253.","DOI":"10.1002\/widm.1253"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Kaiyang Zhou Jingkang Yang Chen\u00a0Change Loy and Ziwei Liu. 2022. Learning to prompt for vision-language models. International Journal of Computer Vision 130 9 (2022) 2337\u20132348.","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3770960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:07:53Z","timestamp":1765008473000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3770960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":43,"alternative-id":["10.1145\/3743093.3770960","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3770960","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}