{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T05:22:56Z","timestamp":1784092976794,"version":"3.55.0"},"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":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730157","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:21:38Z","timestamp":1752456098000},"page":"4004-4009","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["MMMORRF: Multimodal Multilingual MOdularized Reciprocal Rank Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1827-2023","authenticated-orcid":false,"given":"Saron","family":"Samuel","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1850-1801","authenticated-orcid":false,"given":"Dan","family":"DeGenaro","sequence":"additional","affiliation":[{"name":"Georgetown University, Washington, DC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0921-1500","authenticated-orcid":false,"given":"Jimena","family":"Guallar-Blasco","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3125-2975","authenticated-orcid":false,"given":"Kate","family":"Sanders","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8508-4758","authenticated-orcid":false,"given":"Seun","family":"Eisape","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8325-1257","authenticated-orcid":false,"given":"Arun","family":"Reddy","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8863-4002","authenticated-orcid":false,"given":"Alexander","family":"Martin","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-880X","authenticated-orcid":false,"given":"Andrew","family":"Yates","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0051-1535","authenticated-orcid":false,"given":"Eugene","family":"Yang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2097-7428","authenticated-orcid":false,"given":"Cameron","family":"Carpenter","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4234-9215","authenticated-orcid":false,"given":"David","family":"Etter","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2357-9807","authenticated-orcid":false,"given":"Efsun","family":"Kayi","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5423-7754","authenticated-orcid":false,"given":"Matthew","family":"Wiesner","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5628-1003","authenticated-orcid":false,"given":"Kenton","family":"Murray","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0239-9989","authenticated-orcid":false,"given":"Reno","family":"Kriz","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"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":"10.1145\/2600428.2609627"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"e_1_3_2_1_3_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arxiv: 1611.09268 [cs.CL] https:\/\/arxiv.org\/abs\/1611.09268","author":"Bajaj Payal","year":"2018","unstructured":"Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2018. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arxiv: 1611.09268 [cs.CL] https:\/\/arxiv.org\/abs\/1611.09268"},{"key":"e_1_3_2_1_4_1","volume-title":"RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter. arxiv: 2405.19465 [cs.CV] https:\/\/arxiv.org\/abs\/2405.19465","author":"Cao Meng","year":"2024","unstructured":"Meng Cao, Haoran Tang, Jinfa Huang, Peng Jin, Can Zhang, Ruyang Liu, Long Chen, Xiaodan Liang, Li Yuan, and Ge Li. 2024. RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter. arxiv: 2405.19465 [cs.CV] https:\/\/arxiv.org\/abs\/2405.19465"},{"key":"e_1_3_2_1_5_1","unstructured":"Brandon Castellano. [n.d.]. PySceneDetect. https:\/\/github.com\/Breakthrough\/PySceneDetect"},{"key":"e_1_3_2_1_6_1","volume-title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset. arxiv: 2304.08345 [cs.LG] https:\/\/arxiv.org\/abs\/2304.08345","author":"Chen Sihan","year":"2023","unstructured":"Sihan Chen, Xingjian He, Longteng Guo, Xinxin Zhu, Weining Wang, Jinhui Tang, and Jing Liu. 2023a. VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset. arxiv: 2304.08345 [cs.LG] https:\/\/arxiv.org\/abs\/2304.08345"},{"key":"e_1_3_2_1_7_1","first-page":"72842","article-title":"Vast: A vision-audio-subtitle-text omni-modality foundation model and dataset","volume":"36","author":"Chen Sihan","year":"2023","unstructured":"Sihan Chen, Handong Li, Qunbo Wang, Zijia Zhao, Mingzhen Sun, Xinxin Zhu, and Jing Liu. 2023b. Vast: A vision-audio-subtitle-text omni-modality foundation model and dataset. Advances in Neural Information Processing Systems, Vol. 36 (2023), 72842-72866.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_8_1","volume-title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset. arxiv: 2305.18500 [cs.CV] https:\/\/arxiv.org\/abs\/2305.18500","author":"Chen Sihan","year":"2023","unstructured":"Sihan Chen, Handong Li, Qunbo Wang, Zijia Zhao, Mingzhen Sun, Xinxin Zhu, and Jing Liu. 2023c. VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset. arxiv: 2305.18500 [cs.CV] https:\/\/arxiv.org\/abs\/2305.18500"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1572114"},{"key":"e_1_3_2_1_10_1","volume-title":"The faiss library. arXiv preprint arXiv:2401.08281","author":"Douze Matthijs","year":"2024","unstructured":"Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazar\u00e9, Maria Lomeli, Lucas Hosseini, and Herv\u00e9 J\u00e9gou. 2024. The faiss library. arXiv preprint arXiv:2401.08281 (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41676-7_27"},{"key":"e_1_3_2_1_12_1","unstructured":"Han Fang Pengfei Xiong Luhui Xu and Yu Chen. 2021a. CLIP2Video: Mastering Video-Text Retrieval via Image CLIP. arxiv: 2106.11097 [cs.CV] https:\/\/arxiv.org\/abs\/2106.11097"},{"key":"e_1_3_2_1_13_1","volume-title":"Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097","author":"Fang Han","year":"2021","unstructured":"Han Fang, Pengfei Xiong, Luhui Xu, and Yu Chen. 2021b. Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097 (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"Advances in Neural Information Processing Systems","author":"Jin Peng","unstructured":"Peng Jin, JinFa Huang, Fenglin Liu, Xian Wu, Shen Ge, Guoli Song, David A. Clifton, and Jie Chen. 2022. Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations. In Advances in Neural Information Processing Systems, Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (Eds.), Vol. 35. 30291-30306."},{"key":"e_1_3_2_1_15_1","volume-title":"Hannah Recknor, Jimena Guallar-Blasco, Alexander Martin, Ronald Colaianni, Nolan King, Eugene Yang, and Benjamin Van Durme.","author":"Kriz Reno","year":"2024","unstructured":"Reno Kriz, Kate Sanders, David Etter, Kenton Murray, Cameron Carpenter, Kelly Van Ochten, Hannah Recknor, Jimena Guallar-Blasco, Alexander Martin, Ronald Colaianni, Nolan King, Eugene Yang, and Benjamin Van Durme. 2024. MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval. arxiv: 2410.11619 [cs.CV] https:\/\/arxiv.org\/abs\/2410.11619"},{"key":"e_1_3_2_1_16_1","volume-title":"Overview of the TREC 2022 NeuCLIR Track. arXiv preprint arXiv:2304","author":"Lawrie Dawn","year":"2023","unstructured":"Dawn Lawrie, Sean MacAvaney, James Mayfield, Paul McNamee, Douglas W Oard, Luca Soldaini, and Eugene Yang. 2023a. Overview of the TREC 2022 NeuCLIR Track. arXiv preprint arXiv:2304.12367 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Overview of the TREC 2023 NeuCLIR Track. arXiv preprint arXiv:2404","author":"Lawrie Dawn","year":"2024","unstructured":"Dawn Lawrie, Sean MacAvaney, James Mayfield, Paul McNamee, Douglas W Oard, Luca Soldaini, and Eugene Yang. 2024. Overview of the TREC 2023 NeuCLIR Track. arXiv preprint arXiv:2404.08071 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28244-7_33"},{"key":"e_1_3_2_1_19_1","volume-title":"TVR: A large-scale dataset for video-subtitle moment retrieval. In Computer Vision-ECCV 2020: 16th European Conference","author":"Lei Jie","year":"2020","unstructured":"Jie Lei, Licheng Yu, Tamara L Berg, and Mohit Bansal. 2020. TVR: A large-scale dataset for video-subtitle moment retrieval. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXI 16. Springer, 447-463."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.329"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"e_1_3_2_1_22_1","volume-title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","author":"Liao Minghui","year":"2022","unstructured":"Minghui Liao, Zhisheng Zou, Zhaoyi Wan, Cong Yao, and Xiang Bai. 2022. Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99736-6_26"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591644"},{"key":"e_1_3_2_1_25_1","unstructured":"Douglas W Oard and Bonnie Jean Dorr. 1998. A survey of multilingual text retrieval. Citeseer."},{"key":"e_1_3_2_1_26_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. arxiv: 2103.00020 [cs.CV] https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"28518","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine Mcleavey, and Ilya Sutskever. 2023. Robust Speech Recognition via Large-Scale Weak Supervision. In Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 28492-28518. https:\/\/proceedings.mlr.press\/v202\/radford23a.html"},{"key":"e_1_3_2_1_28_1","unstructured":"Kate Sanders David Etter Reno Kriz and Benjamin Van Durme. 2023. MultiVENT: Multilingual Videos of Events with Aligned Natural Text. arxiv: 2307.03153 [cs.IR] https:\/\/arxiv.org\/abs\/2307.03153"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00727"},{"key":"e_1_3_2_1_30_1","volume-title":"MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval. arxiv: 2408.10575 [cs.CV] https:\/\/arxiv.org\/abs\/2408.10575","author":"Tang Haoran","year":"2024","unstructured":"Haoran Tang, Meng Cao, Jinfa Huang, Ruyang Liu, Peng Jin, Ge Li, and Xiaodan Liang. 2024. MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval. arxiv: 2408.10575 [cs.CV] https:\/\/arxiv.org\/abs\/2408.10575"},{"key":"e_1_3_2_1_31_1","volume-title":"Digital video archives: Managing through metadata. Building a national strategy for digital preservation: Issues in digital media archiving","author":"Wactlar Howard D","year":"2002","unstructured":"Howard D Wactlar and Michael G Christel. 2002. Digital video archives: Managing through metadata. Building a national strategy for digital preservation: Issues in digital media archiving, Vol. 84 (2002), 99."},{"key":"e_1_3_2_1_32_1","volume-title":"A comprehensive survey on cross-modal retrieval. arXiv preprint 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 preprint arXiv:1607.06215 (2016)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Yi Wang Kunchang Li Xinhao Li Jiashuo Yu Yinan He Guo Chen Baoqi Pei Rongkun Zheng Jilan Xu Zun Wang et al. 2024. Internvideo2: Scaling video foundation models for multimodal video understanding. arXiv preprint arXiv:2403.15377 (2024).","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110818"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_37_1","unstructured":"Hongwei Xue Yuchong Sun Bei Liu Jianlong Fu Ruihua Song Houqiang Li and Jiebo Luo. 2023. CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment. arxiv: 2209.06430 [cs.CV] https:\/\/arxiv.org\/abs\/2209.06430"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657955"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_4"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531886"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Xiaohua Zhai Basil Mustafa Alexander Kolesnikov and Lucas Beyer. 2023. Sigmoid Loss for Language Image Pre-Training. arxiv: 2303.15343 [cs.CV] https:\/\/arxiv.org\/abs\/2303.15343","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_2_1_42_1","first-page":"35549","article-title":"Towards video text visual question answering: Benchmark and baseline","volume":"35","author":"Zhao Minyi","year":"2022","unstructured":"Minyi Zhao, Bingjia Li, Jie Wang, Wanqing Li, Wenjing Zhou, Lan Zhang, Shijie Xuyang, Zhihang Yu, Xinkun Yu, Guangze Li, et al. 2022. Towards video text visual question answering: Benchmark and baseline. Advances in Neural Information Processing Systems, Vol. 35 (2022), 35549-35562.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_43_1","unstructured":"Bin Zhu Bin Lin Munan Ning Yang Yan Jiaxi Cui HongFa Wang Yatian Pang Wenhao Jiang Junwu Zhang Zongwei Li Wancai Zhang Zhifeng Li Wei Liu and Li Yuan. 2024. LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment. arxiv: 2310.01852 [cs.CV] https:\/\/arxiv.org\/abs\/2310.01852"}],"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\/3726302.3730157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:29:27Z","timestamp":1755887367000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730157"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":43,"alternative-id":["10.1145\/3726302.3730157","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730157","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"}}]}}