{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:29:36Z","timestamp":1764588576910,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T00:00:00Z","timestamp":1717977600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"EPSRC","award":["EP\/V002740\/2"],"award-info":[{"award-number":["EP\/V002740\/2"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,10]]},"DOI":"10.1145\/3664524.3675369","type":"proceedings-article","created":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T18:24:15Z","timestamp":1724869455000},"page":"45-50","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi Modal Fusion for Video Retrieval based on CLIP Guide Feature Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8449-974X","authenticated-orcid":false,"given":"Guanfeng","family":"Wu","sequence":"first","affiliation":[{"name":"School of Mathematics, Southwest Jiaotong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1802-3086","authenticated-orcid":false,"given":"Abbas","family":"Haider","sequence":"additional","affiliation":[{"name":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0289-6790","authenticated-orcid":false,"given":"Ivor","family":"Spence","sequence":"additional","affiliation":[{"name":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2633-6015","authenticated-orcid":false,"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-023-09425-2"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3040847"},{"key":"e_1_3_2_1_4_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_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2982779"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080920"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3227416"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings, Part IV 16","author":"Gabeur Valentin","year":"2020","unstructured":"Valentin Gabeur, Chen Sun, Karteek Alahari, and Cordelia Schmid. 2020. Multi-modal transformer for video retrieval. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part IV 16. Springer, 214\u2013229."},{"key":"e_1_3_2_1_9_1","volume-title":"Text-to-text pre-training for data-to-text tasks. arXiv preprint arXiv:2005.10433","author":"Kale Mihir","year":"2020","unstructured":"Mihir Kale and Abhinav Rastogi. 2020. Text-to-text pre-training for data-to-text tasks. arXiv preprint arXiv:2005.10433 (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2830110"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00041"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-4962-9"},{"key":"e_1_3_2_1_17_1","volume-title":"Uncovering hidden challenges in query-based video moment retrieval. arXiv preprint arXiv:2009.00325","author":"Otani Mayu","year":"2020","unstructured":"Mayu Otani, Yuta Nakashima, Esa Rahtu, and Janne Heikkil\u00e4. 2020. Uncovering hidden challenges in query-based video moment retrieval. arXiv preprint arXiv:2009.00325 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11722-1"},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on machine learning. PMLR, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_2_1_20_1","volume-title":"Language models are unsupervised multitask learners. OpenAI blog 1, 8","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9."},{"key":"e_1_3_2_1_21_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter\u00a0J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21, 140 (2020), 1\u201367.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Soft Computing and Pattern Recognition. Springer, 502\u2013511","author":"Ravi Srihitha","year":"2021","unstructured":"Srihitha Ravi, Shikha Chauhan, Sai\u00a0Harshini Yadlapallii, K Jagruth, and VM Manikandan. 2021. A Novel Educational Video Retrieval System Based on the Textual Information. In International Conference on Soft Computing and Pattern Recognition. Springer, 502\u2013511."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118258"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103557"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357503"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222286"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Phuket Thailand","acronym":"ICMR '24"},"container-title":["Proceedings of 2024 ACM ICMR Workshop on Multimodal Video Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664524.3675369","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664524.3675369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T20:13:57Z","timestamp":1755980037000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664524.3675369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,10]]},"references-count":29,"alternative-id":["10.1145\/3664524.3675369","10.1145\/3664524"],"URL":"https:\/\/doi.org\/10.1145\/3664524.3675369","relation":{},"subject":[],"published":{"date-parts":[[2024,6,10]]},"assertion":[{"value":"2024-08-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}