{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:03:17Z","timestamp":1750309397590,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"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":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681469","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"7424-7433","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DQG: Database Question Generation for Exact Text-based Image Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0110-7208","authenticated-orcid":false,"given":"Rintaro","family":"Yanagi","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST), Tukuba, Ibaraki, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4474-3995","authenticated-orcid":false,"given":"Ren","family":"Togo","sequence":"additional","affiliation":[{"name":"Hokkaido University, Sapporo, Hokkaido, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5332-8112","authenticated-orcid":false,"given":"Takahiro","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Hokkaido University, Sapporo, Hokkaido, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1496-1761","authenticated-orcid":false,"given":"Miki","family":"Haseyama","sequence":"additional","affiliation":[{"name":"Hokkaido University, Sapporo, Hokkaido, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331265"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-007-0103-1"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the International Conference on Very Large Data Bases. 201--210","author":"Bartolini Ilaria","year":"2001","unstructured":"Ilaria Bartolini, Paolo Ciaccia, and Florian Waas. 2001. FeedbackBypass: A new approach to interactive similarity query processing. In Proceedings of the International Conference on Very Large Data Bases. 201--210."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the International Conference on Signal Processing and Multimedia Applications. 1--10","author":"Bartolini Ilaria","year":"2011","unstructured":"Ilaria Bartolini, Marco Patella, and Guido Stromei. 2011. The windsurf library for the efficient retrieval of multimedia hierarchical data. In Proceedings of the International Conference on Signal Processing and Multimedia Applications. 1--10."},{"key":"e_1_3_2_1_6_1","volume-title":"Evaluation of text generation: A survey. arXiv preprint arXiv:2006.14799","author":"Celikyilmaz Asli","year":"2020","unstructured":"Asli Celikyilmaz, Elizabeth Clark, and Jianfeng Gao. 2020. Evaluation of text generation: A survey. arXiv preprint arXiv:2006.14799 (2020)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591758"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1101826.1101866"},{"key":"e_1_3_2_1_10_1","volume-title":"Google Brain Toronto, and Sanja Fidler.","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri, David J Fleet, Jamie Ryan Kiros, Google Brain Toronto, and Sanja Fidler. 2017. VSE : Improving visual-semantic embeddings with hard negatives. arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2957948"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6283"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_14_1","unstructured":"Xiaoxiao Guo Hui Wu Yu Cheng Steven Rennie Gerald Tesauro and Rogerio Feris. 2018. Dialog-based interactive image retrieval. In Advances in Neural Information Processing Systems. 678--688."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Harold Hotelling. 1992. Relations between two sets of variates. In Breakthroughs in statistics. 162--190.","DOI":"10.1007\/978-1-4612-4380-9_14"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"e_1_3_2_1_17_1","volume-title":"Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144","author":"Jang Eric","year":"2016","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2016. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02243"},{"key":"e_1_3_2_1_20_1","volume-title":"Zemel","author":"Kiros Ryan","year":"2014","unstructured":"Ryan Kiros, Ruslan Salakhutdinov, and Richard S. Zemel. 2014. Unifying visual-semantic embeddings with multimodal neural language models. arXiv:1411.2539 (2014)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_22_1","volume-title":"Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach. arXiv preprint arXiv:2406.03411","author":"Lee Yu Sangwon","year":"2024","unstructured":"et aland Yu Sangwon Lee, Saehyung, Junsung Park, Jihun Yi, and Sungroh Yoon. 2024. Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach. arXiv preprint arXiv:2406.03411 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Levy Matan","year":"2024","unstructured":"Matan Levy, Rami Ben-Ari, Nir Darshan, and Dani Lischinski. 2024. Chatting makes perfect: Chat-based image retrieval. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_24_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_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.05.004"},{"volume-title":"Proceedings of the IEEE European Conference on Computer Vision. 740--755","author":"Lin Tsung Yi","key":"e_1_3_2_1_27_1","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 Proceedings of the IEEE European Conference on Computer Vision. 740--755."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.04.037"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2536798"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01361"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09292-9"},{"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\/WACV56688.2023.00121"},{"key":"e_1_3_2_1_35_1","volume-title":"Paolo Bolettieri, Andreas Leibetseder, et al.","author":"Rossetto Luca","year":"2020","unstructured":"Luca Rossetto, Ralph Gasser, Jakub Lokoc, Werner Bailer, Klaus Schoeffmann, Bernd Muenzer, Tomas Soucek, Phuong Anh Nguyen, Paolo Bolettieri, Andreas Leibetseder, et al. 2020. Interactive video retrieval in the age of deep learning-detailed evaluation of vbs 2019. IEEE Transactions on Multimedia (2020)."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the International Conference on Very Large Data Bases","volume":"97","author":"Seidl Thomas","year":"1997","unstructured":"Thomas Seidl and Hans-Peter Kriegel. 1997. Efficient user-adaptable similarity search in large multimedia databases. In Proceedings of the International Conference on Very Large Data Bases, Vol. 97. 506--515."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.895972"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"e_1_3_2_1_39_1","volume-title":"Drill-down: Interactive retrieval of complex scenes using natural language queries. In Advances in Neural Information Processing Systems. 2651--2661.","author":"Tan Fuwen","year":"2019","unstructured":"Fuwen Tan, Paola Cascante-Bonilla, Xiaoxiao Guo, Hui Wu, Song Feng, and Vicente Ordonez. 2019. Drill-down: Interactive retrieval of complex scenes using natural language queries. In Advances in Neural Information Processing Systems. 2651--2661."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11321"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654948"},{"key":"e_1_3_2_1_43_1","volume-title":"A comprehensive survey on cross-modal retrieval. arXiv:1607.06215","author":"Wang Kaiye","year":"2016","unstructured":"Kaiye Wang, Qiyue Yin, Wei Wang, Shu Wu, and Liang Wang. 2016. A comprehensive survey on cross-modal retrieval. arXiv:1607.06215 (2016)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2992187"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2014.53"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1109\/TKDE.2013.70","article-title":"EMR: A scalable graph-based ranking model for content-based image retrieval","volume":"27","author":"Xu Bin","year":"2013","unstructured":"Bin Xu, Jiajun Bu, Chun Chen, Can Wang, Deng Cai, and Xiaofei He. 2013. EMR: A scalable graph-based ranking model for content-based image retrieval. IEEE Transactions on Knowledge and Data Engineering, Vol. 27, 1 (2013), 102--114.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the International Conference on Machine Learning. 2048--2057","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In Proceedings of the International Conference on Machine Learning. 2048--2057."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475681"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3444685.3446290"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2023.3238280"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00514"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2284755"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00223"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380126"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2490823"},{"key":"e_1_3_2_1_59_1","volume-title":"USER: Unified semantic enhancement with momentum contrast for image-text retrieval","author":"Zhang Yan","year":"2024","unstructured":"Yan Zhang, Zhong Ji, Di Wang, Yanwei Pang, and Xuelong Li. 2024. USER: Unified semantic enhancement with momentum contrast for image-text retrieval. IEEE TIP (2024)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"e_1_3_2_1_61_1","volume-title":"Recent advance in content-based image retrieval: A literature survey. arXiv:1706.06064","author":"Zhou Wengang","year":"2017","unstructured":"Wengang Zhou, Houqiang Li, and Qi Tian. 2017. Recent advance in content-based image retrieval: A literature survey. arXiv:1706.06064 (2017)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681469","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:47Z","timestamp":1750294667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681469"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":61,"alternative-id":["10.1145\/3664647.3681469","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681469","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}