{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:03:46Z","timestamp":1776107026276,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"LUMI supercomputer \/ CSC Finland","award":["462000189"],"award-info":[{"award-number":["462000189"]}]},{"name":"LUMI supercomputer \/ CSC Finland","award":["462000139"],"award-info":[{"award-number":["462000139"]}]},{"name":"Academy of Finland","award":["345791"],"award-info":[{"award-number":["345791"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3592038","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"2261-2265","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via Prompting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7088-2331","authenticated-orcid":false,"given":"Zixin","family":"Guo","sequence":"first","affiliation":[{"name":"Aalto University, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8840-3079","authenticated-orcid":false,"given":"Tzu-Jui Julius","family":"Wang","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8658-8890","authenticated-orcid":false,"given":"Selen","family":"Pehlivan","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6317-9752","authenticated-orcid":false,"given":"Abduljalil","family":"Radman","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7218-3131","authenticated-orcid":false,"given":"Jorma","family":"Laaksonen","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katie Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. arXiv preprint arXiv:2204.14198 (2022)."},{"key":"e_1_3_2_2_2_1","volume-title":"Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254","author":"Bao Hangbo","year":"2021","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2021. Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)."},{"key":"e_1_3_2_2_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. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings, Part XIX. Springer, 395--412","author":"Byun Jaeseok","year":"2022","unstructured":"Jaeseok Byun, Taebaek Hwang, Jianlong Fu, and Taesup Moon. 2022. GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XIX. Springer, 395--412."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.742"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_9_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_11_1","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume":"33","author":"Gan Zhe","year":"2020","unstructured":"Zhe Gan, Yen-Chun Chen, Linjie Li, Chen Zhu, Yu Cheng, and Jingjing Liu. 2020. Large-scale adversarial training for vision-and-language representation learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 6616--6628.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-short.5"},{"key":"e_1_3_2_2_13_1","volume-title":"International Conference on Machine Learning. PMLR, 4904--4916","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--4916."},{"key":"e_1_3_2_2_14_1","volume-title":"International Conference on Machine Learning. PMLR, 5583--5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. Vilt: Vision-and-language transformer without convolution or region supervision. In International Conference on Machine Learning. PMLR, 5583--5594."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Chenliang Li Haiyang Xu Junfeng Tian Wei Wang Ming Yan Bin Bi Jiabo Ye Hehong Chen Guohai Xu Zheng Cao et al. 2022c. mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections. arXiv preprint arXiv:2205.12005 (2022).","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"e_1_3_2_2_16_1","volume-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv preprint arXiv:2301.12597","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. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_2_17_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. 2022b. 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_2_18_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021b. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, Vol. 34 (2021), 9694--9705."},{"key":"e_1_3_2_2_19_1","volume-title":"Unsupervised vision-and-language pre-training without parallel images and captions. arXiv preprint arXiv:2010.12831","author":"Li Liunian Harold","year":"2020","unstructured":"Liunian Harold Li, Haoxuan You, Zhecan Wang, Alireza Zareian, Shih-Fu Chang, and Kai-Wei Chang. 2020b. Unsupervised vision-and-language pre-training without parallel images and captions. arXiv preprint arXiv:2010.12831 (2020)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"e_1_3_2_2_21_1","volume-title":"UNIMO-2: end-to-end unified vision-language grounded learning. arXiv preprint arXiv:2203.09067","author":"Li Wei","year":"2022","unstructured":"Wei Li, Can Gao, Guocheng Niu, Xinyan Xiao, Hao Liu, Jiachen Liu, Hua Wu, and Haifeng Wang. 2022a. UNIMO-2: end-to-end unified vision-language grounded learning. arXiv preprint arXiv:2203.09067 (2022)."},{"key":"e_1_3_2_2_22_1","volume-title":"Proceedings, Part XXX 16","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. 2020a. Oscar: Object-semantics aligned pre-training for vision-language tasks. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXX 16. Springer, 121--137."},{"key":"e_1_3_2_2_23_1","volume-title":"Proceedings, Part V 13","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_2_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"e_1_3_2_2_25_1","volume-title":"Visual Classification via Description from Large Language Models. arXiv preprint arXiv:2210.07183","author":"Menon Sachit","year":"2022","unstructured":"Sachit Menon and Carl Vondrick. 2022. Visual Classification via Description from Large Language Models. arXiv preprint arXiv:2210.07183 (2022)."},{"key":"e_1_3_2_2_26_1","volume-title":"Im2text: Describing images using 1 million captioned photographs. Advances in neural information processing systems","author":"Ordonez Vicente","year":"2011","unstructured":"Vicente Ordonez, Girish Kulkarni, and Tamara Berg. 2011. Im2text: Describing images using 1 million captioned photographs. Advances in neural information processing systems, Vol. 24 (2011)."},{"key":"e_1_3_2_2_27_1","volume-title":"What does a platypus look like? Generating customized prompts for zero-shot image classification. arXiv preprint arXiv:2209.03320","author":"Pratt Sarah","year":"2022","unstructured":"Sarah Pratt, Rosanne Liu, and Ali Farhadi. 2022. What does a platypus look like? Generating customized prompts for zero-shot image classification. arXiv preprint arXiv:2209.03320 (2022)."},{"key":"e_1_3_2_2_28_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_2_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"e_1_3_2_2_31_1","volume-title":"International conference on machine learning. PMLR, 10347--10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347--10357."},{"key":"e_1_3_2_2_32_1","volume-title":"International Conference on Machine Learning. PMLR, 22680--22690","author":"Wang Teng","year":"2022","unstructured":"Teng Wang, Wenhao Jiang, Zhichao Lu, Feng Zheng, Ran Cheng, Chengguo Yin, and Ping Luo. 2022b. Vlmixer: Unpaired vision-language pre-training via cross-modal cutmix. In International Conference on Machine Learning. PMLR, 22680--22690."},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 1073--1083","author":"Julius Wang Tzu-Jui","year":"2023","unstructured":"Tzu-Jui Julius Wang, Jorma Laaksonen, Tomas Langer, Heikki Arponen, and Tom E Bishop. 2023. Learning by Hallucinating: Vision-Language Pre-training with Weak Supervision. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 1073--1083."},{"key":"e_1_3_2_2_34_1","volume-title":"Saksham Singhal, Subhojit Som, et al.","author":"Wang Wenhui","year":"2022","unstructured":"Wenhui Wang, Hangbo Bao, Li Dong, Johan Bjorck, Zhiliang Peng, Qiang Liu, Kriti Aggarwal, Owais Khan Mohammed, Saksham Singhal, Subhojit Som, et al. 2022a. Image as a foreign language: Beit pretraining for all vision and vision-language tasks. arXiv preprint arXiv:2208.10442 (2022)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"e_1_3_2_2_36_1","volume-title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification. arXiv preprint arXiv:2211.11158","author":"Yang Yue","year":"2022","unstructured":"Yue Yang, Artemis Panagopoulou, Shenghao Zhou, Daniel Jin, Chris Callison-Burch, and Mark Yatskar. 2022b. Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification. arXiv preprint arXiv:2211.11158 (2022)."},{"key":"e_1_3_2_2_37_1","first-page":"23634","article-title":"Merlot: Multimodal neural script knowledge models","volume":"34","author":"Zellers Rowan","year":"2021","unstructured":"Rowan Zellers, Ximing Lu, Jack Hessel, Youngjae Yu, Jae Sung Park, Jize Cao, Ali Farhadi, and Yejin Choi. 2021. Merlot: Multimodal neural script knowledge models. Advances in Neural Information Processing Systems, Vol. 34 (2021), 23634--23651.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16485--16494","author":"Zhou Mingyang","year":"2022","unstructured":"Mingyang Zhou, Licheng Yu, Amanpreet Singh, Mengjiao Wang, Zhou Yu, and Ning Zhang. 2022. Unsupervised vision-and-language pre-training via retrieval-based multi-granular alignment. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16485--16494."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3592038","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3592038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:49Z","timestamp":1750178269000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3592038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":40,"alternative-id":["10.1145\/3539618.3592038","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3592038","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}