{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:10:30Z","timestamp":1792080630099,"version":"4.4.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 62376137"],"award-info":[{"award-number":["No. 62376137"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3729979","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T14:55:26Z","timestamp":1752504926000},"page":"803-812","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["FiRE: Enhancing MLLMs with Fine-Grained Context Learning for Complex Image Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0751-166X","authenticated-orcid":false,"given":"Bohan","family":"Hou","sequence":"first","affiliation":[{"name":"Shandong University, Qingdao, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5768-5467","authenticated-orcid":false,"given":"Haoqiang","family":"Lin","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, Shandong, 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":"City University of Hong Kong, Hong Kong, Hong Kong"}],"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, 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\/0000-0003-2926-4416","authenticated-orcid":false,"given":"Xiangyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, 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":"10.1145\/3617597"},{"key":"e_1_3_2_1_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. In Advances in neural information processing systems. 1877-1901."},{"key":"e_1_3_2_1_4_1","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung Hyung Won","year":"2024","unstructured":"Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, et al., 2024. Scaling instruction-finetuned language models. Journal of Machine Learning Research, Vol. 25, 70 (2024), 1-53.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, 6904-6913","author":"Goyal Yash","unstructured":"Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, and Devi Parikh. [n.d.]. Making the v in vqa matter: Elevating the role of image understanding in visual question answering. In Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, 6904-6913."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01256"},{"key":"e_1_3_2_1_9_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00067"},{"key":"e_1_3_2_1_11_1","volume-title":"E5-v: Universal embeddings with multimodal large language models. arXiv preprint arXiv:2407.12580","author":"Jiang Ting","year":"2024","unstructured":"Ting Jiang, Minghui Song, Zihan Zhang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang, Deqing Wang, and Fuzhen Zhuang. 2024. E5-v: Universal embeddings with multimodal large language models. arXiv preprint arXiv:2407.12580 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1-15","author":"Karthik Shyamgopal","year":"2023","unstructured":"Shyamgopal Karthik, Karsten Roth, Massimiliano Mancini, and Zeynep Akata. 2023. Vision-by-language for training-free compositional image retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1-15."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 17283-17300","author":"Koh Jing Yu","year":"2023","unstructured":"Jing Yu Koh, Ruslan Salakhutdinov, and Daniel Fried. 2023. Grounding language models to images for multimodal inputs and outputs. In Proceedings of the International Conference on Machine Learning. PMLR, 17283-17300."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28081"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 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 Proceedings of the International Conference on Machine Learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 1-21","author":"Li Wei","year":"2024","unstructured":"Wei Li, Hehe Fan, Yongkang Wong, Yi Yang, and Mohan Kankanhalli. 2024. Improving Context Understanding in Multimodal Large Language Models via Multimodal Composition Learning. In Proceedings of the International Conference on Machine Learning. PMLR, 1-21."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657831"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_19_1","volume-title":"Zero-shot composed text-image retrieval. arXiv preprint arXiv:2306.07272","author":"Liu Yikun","year":"2023","unstructured":"Yikun Liu, Jiangchao Yao, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2023. Zero-shot composed text-image retrieval. arXiv preprint arXiv:2306.07272 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"e_1_3_2_1_21_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov I","year":"2017","unstructured":"I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_23_1","volume-title":"Generative representational instruction tuning. arXiv preprint arXiv:2402.09906","author":"Muennighoff Niklas","year":"2024","unstructured":"Niklas Muennighoff, Hongjin Su, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, and Douwe Kiela. 2024. Generative representational instruction tuning. arXiv preprint arXiv:2402.09906 (2024)."},{"key":"e_1_3_2_1_24_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. (2022) 27730-27744."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00735"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Bryan A. Plummer Liwei Wang Chris M. Cervantes Juan C. Caicedo Julia Hockenmaier and Svetlana Lazebnik. 2016. Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models. (2016).","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_1_27_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_28_1","volume-title":"ZeRO: Memory Optimization Towards Training A Trillion Parameter Models. arXiv preprint arXiv","author":"Rajbhandari Samyam","year":"1910","unstructured":"Samyam Rajbhandari, Jeff Rasley, Olatunji Ruwase, and Yuxiong He. 2019. ZeRO: Memory Optimization Towards Training A Trillion Parameter Models. arXiv preprint arXiv: 1910.02054 (2019)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123314"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28324"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331407"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657727"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401423"},{"key":"e_1_3_2_1_37_1","volume-title":"Shelby Heinecke, Huan Wang, Yejin Choi, Ludwig Schmidt, Zeyuan Chen, Silvio Savarese, Juan Carlos Niebles, Caiming Xiong, and Ran Xu.","author":"Xue Le","year":"2024","unstructured":"Le Xue, Manli Shu, Anas Awadalla, Jun Wang, An Yan, Senthil Purushwalkam, Honglu Zhou, Viraj Prabhu, Yutong Dai, Michael S. Ryoo, Shrikant Kendre, Jieyu Zhang, Can Qin, Shu Zhang, Chia-Chih Chen, Ning Yu, Juntao Tan, Tulika Manoj Awalgaonkar, Shelby Heinecke, Huan Wang, Yejin Choi, Ludwig Schmidt, Zeyuan Chen, Silvio Savarese, Juan Carlos Niebles, Caiming Xiong, and Ran Xu. 2024. xGen-MM (BLIP-3): A Family of Open Large Multimodal Models. arXiv preprint arXiv:2408.08872 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657740"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the European Conference on Computer Vision. Springer, 310-325","author":"Zhang Beichen","year":"2024","unstructured":"Beichen Zhang, Pan Zhang, Xiaoyi Dong, Yuhang Zang, and Jiaqi Wang. 2024b. Long-CLIP: Unlocking the Long-Text Capability of CLIP. In Proceedings of the European Conference on Computer Vision. Springer, 310-325."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 1-18","author":"Zhang Kai","year":"2024","unstructured":"Kai Zhang, Yi Luan, Hexiang Hu, Kenton Lee, Siyuan Qiao, Wenhu Chen, Yu Su, and Ming-Wei Chang. 2024a. Magiclens: Self-supervised image retrieval with open-ended instructions. In Proceedings of the International Conference on Machine Learning. PMLR, 1-18."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"}],"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\/3726302.3729979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:33:57Z","timestamp":1755887637000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3729979"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":41,"alternative-id":["10.1145\/3726302.3729979","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3729979","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"}}]}}