{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:27:39Z","timestamp":1792513659633,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":47,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657741","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2188-2198","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["<i>CFIR:<\/i>\n            Fast and Effective Long-Text To Image Retrieval for Large Corpora"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2008-960X","authenticated-orcid":false,"given":"Zijun","family":"Long","sequence":"first","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3925-4951","authenticated-orcid":false,"given":"Xuri","family":"Ge","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2751-2087","authenticated-orcid":false,"given":"Richard","family":"McCreadie","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9228-1759","authenticated-orcid":false,"given":"Joemon M.","family":"Jose","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Imram: Iterative matching with recurrent attention memory for cross-modal image-text retrieval. In CVPR. 12655--12663.","author":"Chen Hui","year":"2020","unstructured":"Hui Chen, Guiguang Ding, Xudong Liu, Zijia Lin, Ji Liu, and Jungong Han. 2020. Imram: Iterative matching with recurrent attention memory for cross-modal image-text retrieval. In CVPR. 12655--12663."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Mehdi Cherti Romain Beaumont Ross Wightman Mitchell Wortsman Gabriel Ilharco Cade Gordon Christoph Schuhmann Ludwig Schmidt and Jenia Jitsev. 2023. Reproducible scaling laws for contrastive language-image learning. In CVPR. 2818--2829.","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"e_1_3_2_1_3_1","volume-title":"Autoaugment: Learning augmentation strategies from data. In CVPR. 113--123.","author":"Cubuk Ekin D","year":"2019","unstructured":"Ekin D Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, and Quoc V Le. 2019. Autoaugment: Learning augmentation strategies from data. In CVPR. 113--123."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3407190"},{"key":"e_1_3_2_1_5_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. NAACL","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. NAACL (2019)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Fangxiang Feng Xiaojie Wang and Ruifan Li. 2014. Cross-modal retrieval with correspondence autoencoder. In ACM MM. 7--16.","DOI":"10.1145\/2647868.2654902"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Xuri Ge Fuhai Chen Joemon M Jose Zhilong Ji Zhongqin Wu and Xiao Liu. 2021. Structured multi-modal feature embedding and alignment for image-sentence retrieval. In ACM MM. 5185--5193.","DOI":"10.1145\/3474085.3475634"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00108"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103716"},{"key":"e_1_3_2_1_10_1","volume-title":"Gilbert: Generative vision-language pre-training for image-text retrieval. In ACM SIGIR. 1379--1388.","author":"Hong Weixiang","year":"2021","unstructured":"Weixiang Hong, Kaixiang Ji, Jiajia Liu, Jian Wang, Jingdong Chen, and Wei Chu. 2021. Gilbert: Generative vision-language pre-training for image-text retrieval. In ACM SIGIR. 1379--1388."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591896"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Yan Huang Qi Wu Chunfeng Song and Liang Wang. 2018. Learning semantic concepts and order for image and sentence matching. In CVPR. 6163--6171.","DOI":"10.1109\/CVPR.2018.00645"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Lyndon S Kennedy Apostol Natsev and Shih-Fu Chang. 2005. Automatic discovery of query-class-dependent models for multimodal search. In ACM MM. 882--891.","DOI":"10.1145\/1101149.1101339"},{"key":"e_1_3_2_1_14_1","volume-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. ACL","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. ACL (2019)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_1_16_1","volume-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In ICML. 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 ICML. PMLR, 12888--12900."},{"key":"e_1_3_2_1_17_1","unstructured":"Kunpeng Li Yulun Zhang Kai Li Yuanyuan Li and Yun Fu. 2019b. Visual semantic reasoning for image-text matching. In ICCV. 4654--4662."},{"key":"e_1_3_2_1_18_1","volume-title":"VisualBERT: A Simple and Performant Baseline for Vision and Language. CoRR","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019a. VisualBERT: A Simple and Performant Baseline for Vision and Language. CoRR , Vol. abs\/1908.03557 (2019)."},{"key":"e_1_3_2_1_19_1","volume-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"Li Xiujun","year":"2020","unstructured":"Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, et al. 2020b. Oscar: Object-semantics aligned pre-training for vision-language tasks. In ECCV. Springer, 121--137."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591633"},{"key":"e_1_3_2_1_21_1","volume-title":"Microsoft coco: Common objects in context","author":"Lin Tsung-Yi","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 ECCV. Springer, 740--755."},{"key":"e_1_3_2_1_22_1","volume-title":"Xiaojun Wan, and Josiah Poon.","author":"Long Siqu","year":"2022","unstructured":"Siqu Long, Soyeon Caren Han, Xiaojun Wan, and Josiah Poon. 2022. Gradual: Graph-based dual-modal representation for image-text matching. In WACV. 3459--3468."},{"key":"e_1_3_2_1_23_1","volume-title":"2023 a. Robollm: Robotic vision tasks grounded on multimodal large language models. arXiv preprint arXiv:2310.10221","author":"Long Zijun","year":"2023","unstructured":"Zijun Long, George Killick, Richard McCreadie, and Gerardo Aragon Camarasa. 2023 a. Robollm: Robotic vision tasks grounded on multimodal large language models. arXiv preprint arXiv:2310.10221 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"ICASSP 2024--2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Long Zijun","unstructured":"Zijun Long, George Killick, Richard McCreadie, and Gerardo Aragon Camarasa. 2024. Multiway-Adapter: Adapting Multimodal Large Language Models for Scalable Image-Text Retrieval. In ICASSP 2024--2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 6580--6584."},{"key":"e_1_3_2_1_25_1","unstructured":"Zijun Long George Killick Richard McCreadie Gerardo Aragon Camarasa and Zaiqiao Meng. 2023 b. When hard negative sampling meets supervised contrastive learning. arXiv preprint arXiv:2308.14893."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Zijun Long George Killick Lipeng Zhuang Richard McCreadie Gerardo Aragon Camarasa and Paul Henderson. 2023 c. Elucidating and overcoming the challenges of label noise in supervised contrastive learning. arXiv preprint arXiv:2311.16481.","DOI":"10.1007\/978-3-031-72949-2_25"},{"key":"e_1_3_2_1_27_1","volume-title":"19th International Conference on Information Systems for Crisis Response and Management (ISCRAM","author":"Long Zijun","year":"2022","unstructured":"Zijun Long and Richard McCreadie. [n.,d.]. Is Multi-Modal Data Key for Crisis Content Categorization on Social Media?. In 19th International Conference on Information Systems for Crisis Response and Management (ISCRAM 2022)."},{"key":"e_1_3_2_1_28_1","volume-title":"LACVIT: A Label-aware Contrastive Fine-tuning Framework for Vision Transformers. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP","author":"Long Zijun","year":"2024","unstructured":"Zijun Long, Richard McCreadie, Gerardo Aragon Camarasa, and Zaiqiao Meng. [n.,d.]. LACVIT: A Label-aware Contrastive Fine-tuning Framework for Vision Transformers. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"2023 d. Crisisvit: A robust vision transformer for crisis image classification. arXiv preprint arXiv:2401.02838","author":"Long Zijun","year":"2023","unstructured":"Zijun Long, Richard McCreadie, and Muhammad Imran. 2023 d. Crisisvit: A robust vision transformer for crisis image classification. arXiv preprint arXiv:2401.02838 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"NeurIPS","volume":"32","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. NeurIPS , Vol. 32 (2019)."},{"key":"e_1_3_2_1_31_1","volume-title":"Learnable Pillar-based Re-ranking for Image-Text Retrieval. ACM SIGIR","author":"Qu Leigang","year":"2023","unstructured":"Leigang Qu, Meng Liu, Wenjie Wang, Zhedong Zheng, Liqiang Nie, and Tat-Seng Chua. 2023. Learnable Pillar-based Re-ranking for Image-Text Retrieval. ACM SIGIR (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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 ICML. PMLR, 8748--8763."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-7068-0"},{"key":"e_1_3_2_1_34_1","volume-title":"Flava: A foundational language and vision alignment model. In CVPR. 15638--15650.","author":"Singh Amanpreet","year":"2022","unstructured":"Amanpreet Singh, Ronghang Hu, Vedanuj Goswami, Guillaume Couairon, Wojciech Galuba, Marcus Rohrbach, and Douwe Kiela. 2022. Flava: A foundational language and vision alignment model. In CVPR. 15638--15650."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Yale Song and Mohammad Soleymani. 2019. Polysemous visual-semantic embedding for cross-modal retrieval. In CVPR. 1979--1988.","DOI":"10.1109\/CVPR.2019.00208"},{"key":"e_1_3_2_1_36_1","volume-title":"Wit: Wikipedia-based image text dataset for multimodal multilingual machine learning. In ACM SIGIR. 2443--2449.","author":"Srinivasan Krishna","year":"2021","unstructured":"Krishna Srinivasan, Karthik Raman, Jiecao Chen, Michael Bendersky, and Marc Najork. 2021. Wit: Wikipedia-based image text dataset for multimodal multilingual machine learning. In ACM SIGIR. 2443--2449."},{"key":"e_1_3_2_1_37_1","volume-title":"Lxmert: Learning cross-modality encoder representations from transformers. In EMNLP-IJCNLP. 5099--5110.","author":"Tan Hao","year":"2019","unstructured":"Hao Tan and Mohit Bansal. 2019. Lxmert: Learning cross-modality encoder representations from transformers. In EMNLP-IJCNLP. 5099--5110."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532028"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Shuhui Wang Yangyu Chen Junbao Zhuo Qingming Huang and Qi Tian. 2018. Joint global and co-attentive representation learning for image-sentence retrieval. In ACM MM. 1398--1406.","DOI":"10.1145\/3240508.3240535"},{"key":"e_1_3_2_1_40_1","volume-title":"Heng Tao Shen, and Jingkuan Song","author":"Wang Tan","year":"2019","unstructured":"Tan Wang, Xing Xu, Yang Yang, Alan Hanjalic, Heng Tao Shen, and Jingkuan Song. 2019. Matching images and text with multi-modal tensor fusion and re-ranking. In ACM MM. 12--20."},{"key":"e_1_3_2_1_41_1","volume-title":"Saksham Singhal, Subhojit Som, et al.","author":"Wang Wenhui","year":"2023","unstructured":"Wenhui Wang, Hangbo Bao, Li Dong, Johan Bjorck, Zhiliang Peng, Qiang Liu, Kriti Aggarwal, Owais Khan Mohammed, Saksham Singhal, Subhojit Som, et al. 2023. Image as a Foreign Language: BEiT Pretraining for Vision and Vision-Language Tasks. In CVPR. 19175--19186."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Yaxiong Wu Craig Macdonald and Iadh Ounis. 2021. Partially observable reinforcement learning for dialog-based interactive recommendation. In ACM RecSys. 241--251.","DOI":"10.1145\/3460231.3474256"},{"key":"e_1_3_2_1_43_1","volume-title":"Krishna Srinivasan, Miriam Redi, St\u00e9phane Clinchant, and Jimmy Lin.","author":"Yang Jheng-Hong","year":"2023","unstructured":"Jheng-Hong Yang, Carlos Lassance, Rafael Sampaio De Rezende, Krishna Srinivasan, Miriam Redi, St\u00e9phane Clinchant, and Jimmy Lin. 2023. AToMiC: An Image\/Text Retrieval Test Collection to Support Multimedia Content Creation. In ACM SIGIR. 2975--2984."},{"key":"e_1_3_2_1_44_1","unstructured":"Zixuan Yi Zijun Long Iadh Ounis Craig Macdonald and Richard Mccreadie. 2023. Large multi-modal encoders for recommendation. arXiv preprint arXiv:2310.20343."},{"key":"e_1_3_2_1_45_1","first-page":"81","article-title":"A survey on content-based retrieval for multimedia databases","volume":"11","author":"Yoshitaka Atsuo","year":"1999","unstructured":"Atsuo Yoshitaka and Tadao Ichikawa. 1999. A survey on content-based retrieval for multimedia databases. IEEE TKDE, Vol. 11, 1 (1999), 81--93.","journal-title":"IEEE TKDE"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591721"}],"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\/3626772.3657741","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:28:49Z","timestamp":1755840529000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":47,"alternative-id":["10.1145\/3626772.3657741","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657741","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"}}]}}