{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:43:10Z","timestamp":1787017390691,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1145\/3696409.3700287","type":"proceedings-article","created":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T04:55:23Z","timestamp":1735361723000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Fine-grained Video Semantic Distillation for Video-Text Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0474-5070","authenticated-orcid":false,"given":"zuyi","family":"pei","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, CN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2861-4288","authenticated-orcid":false,"given":"Baoli","family":"Sun","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, CN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5011-9726","authenticated-orcid":false,"given":"zhihui","family":"wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, CN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3882-2205","authenticated-orcid":false,"given":"Haojie","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong University of Science and Technology, Qingdao, CN"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Adrien Bardes Quentin Garrido Jean Ponce Xinlei Chen Michael\u00a0G. Rabbat Yann LeCun Mahmoud Assran and Nicolas Ballas. 2024. Revisiting Feature Prediction for Learning Visual Representations from Video. CoRR abs\/2404.08471 (2024). 10.48550\/ARXIV.2404.08471 arXiv:https:\/\/arXiv.org\/abs\/2404.08471","DOI":"10.48550\/ARXIV.2404.08471"},{"key":"e_1_3_3_1_3_2","first-page":"4","volume-title":"ICML","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In ICML , Vol.\u00a02. 4."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"e_1_3_3_1_6_2","unstructured":"Han Fang Pengfei Xiong Luhui Xu and Yu Chen. 2021. Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.11097 (2021)."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_3_1_8_2","unstructured":"Zijian Gao Jingyu Liu Weiqi Sun Sheng Chen Dedan Chang and Lili Zhao. 2021. Clip2tv: Align match and distill for video-text retrieval. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2111.05610 (2021)."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01025"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_3_1_12_2","series-title":"Proceedings of Machine Learning Research","first-page":"19730","volume-title":"International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA","volume":"202","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven C.\u00a0H. Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA(Proceedings of Machine Learning Research, Vol.\u00a0202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 19730\u201319742. https:\/\/proceedings.mlr.press\/v202\/li23q.html"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"e_1_3_3_1_14_2","unstructured":"Yang Liu Samuel Albanie Arsha Nagrani and Andrew Zisserman. 2019. Use what you have: Video retrieval using representations from collaborative experts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1907.13487 (2019)."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"e_1_3_3_1_16_2","unstructured":"Huaishao Luo Lei Ji Ming Zhong Yang Chen Wen Lei Nan Duan and Tianrui Li. 2021. CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval. CoRR abs\/2104.08860 (2021). arXiv:https:\/\/arXiv.org\/abs\/2104.08860https:\/\/arxiv.org\/abs\/2104.08860"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"e_1_3_3_1_18_2","series-title":"Proceedings of Machine Learning Research","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event","volume":"139","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, 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.\u00a0139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748\u20138763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_3_1_21_2","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023","author":"Xue Hongwei","year":"2023","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 Alignment. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/pdf?id=GNjzMAgawq"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"}],"event":{"name":"MMAsia '24: ACM Multimedia Asia","location":"Auckland New Zealand","acronym":"MMAsia '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 6th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700287","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696409.3700287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:10:16Z","timestamp":1750281016000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":22,"alternative-id":["10.1145\/3696409.3700287","10.1145\/3696409"],"URL":"https:\/\/doi.org\/10.1145\/3696409.3700287","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}