{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:38:22Z","timestamp":1783543102577,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T00:00:00Z","timestamp":1709510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,4]]},"DOI":"10.1145\/3616855.3635757","type":"proceedings-article","created":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T18:18:12Z","timestamp":1709576292000},"page":"369-377","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Text-Video Retrieval via Multi-Modal Hypergraph Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1612-4644","authenticated-orcid":false,"given":"Qian","family":"Li","sequence":"first","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1246-1740","authenticated-orcid":false,"given":"Lixin","family":"Su","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1241-0686","authenticated-orcid":false,"given":"Jiashu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Wilfrid Laurier University, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3016-4351","authenticated-orcid":false,"given":"Long","family":"Xia","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7147-5666","authenticated-orcid":false,"given":"Hengyi","family":"Cai","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3622-3399","authenticated-orcid":false,"given":"Suqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9519-903X","authenticated-orcid":false,"given":"Hengzhu","family":"Tang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8032-6374","authenticated-orcid":false,"given":"Junfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3987-4349","authenticated-orcid":false,"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,3,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval. In 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021","author":"Bain Max","year":"2021","unstructured":"Max Bain, Arsha Nagrani, G\u00fcl Varol, and Andrew Zisserman. 2021. Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval. In 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10--17, 2021. IEEE, 1708--1718. https:\/\/doi.org\/10.1109\/ ICCV48922.2021.00175"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"key":"e_1_3_2_1_3_1","volume-title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss. CoRR abs\/2109.04290","author":"Cheng Xing","year":"2021","unstructured":"Xing Cheng, Hezheng Lin, XiangyuWu, Fan Yang, and Dong Shen. 2021. Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss. CoRR abs\/2109.04290 (2021). arXiv:2109.04290 https:\/\/arxiv.org\/abs\/2109. 04290"},{"key":"e_1_3_2_1_4_1","volume-title":"Users' relevance criteria in image retrieval in American history. Information processing & management 38, 5","author":"Choi Youngok","year":"2002","unstructured":"Youngok Choi and Edie M Rasmussen. 2002. Users' relevance criteria in image retrieval in American history. Information processing & management 38, 5 (2002), 695--726."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","volume":"1","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. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2--7, 2019, Volume 1 (Long and Short Papers). 4171-- 4186."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548365"},{"key":"e_1_3_2_1_9_1","volume-title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP. CoRR abs\/2106.11097","author":"Fang Han","year":"2021","unstructured":"Han Fang, Pengfei Xiong, Luhui Xu, and Yu Chen. 2021. CLIP2Video: Mastering Video-Text Retrieval via Image CLIP. CoRR abs\/2106.11097 (2021). arXiv:2106.11097 https:\/\/arxiv.org\/abs\/2106.11097"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--58548--8_13"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102067"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01243"},{"key":"e_1_3_2_1_14_1","volume-title":"Visual spatio-temporal relation-enhanced network for cross-modal text-video retrieval. arXiv preprint arXiv:2110.15609","author":"Han Ning","year":"2021","unstructured":"Ning Han, Jingjing Chen, Guangyi Xiao, Yawen Zeng, Chuhao Shi, and Hao Chen. 2021. Visual spatio-temporal relation-enhanced network for cross-modal text-video retrieval. arXiv preprint arXiv:2110.15609 (2021)."},{"key":"e_1_3_2_1_15_1","volume-title":"Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment. CoRR abs\/2305.12218","author":"Jin Peng","year":"2023","unstructured":"Peng Jin, Hao Li, Zesen Cheng, Jinfa Huang, ZhennanWang, Li Yuan, Chang Liu, and Jie Chen. 2023. Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment. CoRR abs\/2305.12218 (2023). https:\/\/doi.org\/10.48550\/ arXiv.2305.12218 arXiv:2305.12218"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01814"},{"key":"e_1_3_2_1_19_1","volume-title":"Reasoning over different types of knowledge graphs: Static, temporal and multi-modal. arXiv preprint arXiv:2212.05767","author":"Liang Ke","year":"2022","unstructured":"Ke Liang, Lingyuan Meng, Meng Liu, Yue Liu, Wenxuan Tu, Siwei Wang, Sihang Zhou, Xinwang Liu, and Fuchun Sun. 2022. Reasoning over different types of knowledge graphs: Static, temporal and multi-modal. arXiv preprint arXiv:2212.05767 (2022)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.094"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"e_1_3_2_1_22_1","volume-title":"30th British Machine Vision Conference 2019, BMVC 2019","author":"Liu Yang","year":"2019","unstructured":"Yang Liu, Samuel Albanie, Arsha Nagrani, and Andrew Zisserman. 2019. Use What You Have: Video retrieval using representations from collaborative experts. In 30th British Machine Vision Conference 2019, BMVC 2019, Cardiff, UK, September 9--12, 2019. BMVA Press, 279. https:\/\/bmvc2019.org\/wp-content\/uploads\/papers\/ 0363-paper.pdf"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531776"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_2_1_26_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Patrick Mandela","year":"2021","unstructured":"Mandela Patrick, Po-Yao Huang, Yuki Markus Asano, Florian Metze, Alexander G. Hauptmann, Jo\u00e3o F. Henriques, and Andrea Vedaldi. 2021. Support-set bottlenecks for video-text representation learning. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=EqoXe2zmhrh"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01820"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139). PMLR, 8748--8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512022"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475515"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592064"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-023-00267--8"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2013.01.004"}],"event":{"name":"WSDM '24: The 17th ACM International Conference on Web Search and Data Mining","location":"Merida Mexico","acronym":"WSDM '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 17th ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635757","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3616855.3635757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:47:17Z","timestamp":1755823637000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635757"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,4]]},"references-count":38,"alternative-id":["10.1145\/3616855.3635757","10.1145\/3616855"],"URL":"https:\/\/doi.org\/10.1145\/3616855.3635757","relation":{},"subject":[],"published":{"date-parts":[[2024,3,4]]},"assertion":[{"value":"2024-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}