{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T22:11:29Z","timestamp":1768083089490,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"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":[[2022,7,6]]},"DOI":"10.1145\/3477495.3531776","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:13Z","timestamp":1657206733000},"page":"1906-1911","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Animating Images to Transfer CLIP for Video-Text Retrieval"],"prefix":"10.1145","author":[{"given":"Yu","family":"Liu","sequence":"first","affiliation":[{"name":"DAMO Academy, Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huai","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianghua","family":"Huang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Chen","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Pan","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lisheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"e_1_3_2_2_6_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy , Lucas Beyer , Alexander Kolesnikov , Dirk Weissenborn , Xiaohua Zhai , Thomas Unterthiner , Mostafa Dehghani , Matthias Minderer , Georg Heigold , Sylvain Gelly , 2020 . An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale . In International Conference on Learning Representations. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"e_1_3_2_2_8_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 . 2021. CLIP2Video: Mastering Video-Text Retrieval via Image CLIP. arXiv preprint arXiv:2106.11097 ( 2021 ). Han Fang, Pengfei Xiong, Luhui Xu, and Yu Chen. 2021. CLIP2Video: Mastering Video-Text Retrieval via Image CLIP. arXiv preprint arXiv:2106.11097 (2021)."},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings, Part IV 16","author":"Gabeur Valentin","year":"2020","unstructured":"Valentin Gabeur , Chen Sun , Karteek Alahari , and Cordelia Schmid . 2020 . Multimodal transformer for video retrieval. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020 , Proceedings, Part IV 16 . Springer, 214--229. Valentin Gabeur, Chen Sun, Karteek Alahari, and Cordelia Schmid. 2020. Multimodal transformer for video retrieval. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part IV 16. Springer, 214--229."},{"key":"e_1_3_2_2_10_1","volume-title":"Scaling up visual and visionlanguage representation learning with noisy text supervision. arXiv preprint arXiv:2102.05918","author":"Jia Chao","year":"2021","unstructured":"Chao Jia , Yinfei Yang , Ye Xia , Yi-Ting Chen , Zarana Parekh , Hieu Pham , Quoc V Le , Yunhsuan Sung , Zhen Li , and Tom Duerig . 2021. Scaling up visual and visionlanguage representation learning with noisy text supervision. arXiv preprint arXiv:2102.05918 ( 2021 ). Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V Le, Yunhsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and visionlanguage representation learning with noisy text supervision. arXiv preprint arXiv:2102.05918 (2021)."},{"key":"e_1_3_2_2_11_1","volume-title":"Unifying visualsemantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539","author":"Kiros Ryan","year":"2014","unstructured":"Ryan Kiros , Ruslan Salakhutdinov , and Richard S Zemel . 2014. Unifying visualsemantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 ( 2014 ). Ryan Kiros, Ruslan Salakhutdinov, and Richard S Zemel. 2014. Unifying visualsemantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma etal 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision 123 1 (2017) 32--73.  Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision 123 1 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"e_1_3_2_2_15_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in Neural Information Processing Systems 34","author":"Li Junnan","year":"2021","unstructured":"Junnan Li , Ramprasaath Selvaraju , Akhilesh Gotmare , Shafiq Joty , Caiming Xiong , and Steven Chu Hong Hoi . 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in Neural Information Processing Systems 34 ( 2021 ). Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"e_1_3_2_2_18_1","volume-title":"Use what you have: Video retrieval using representations from collaborative experts. arXiv preprint arXiv:1907.13487","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. arXiv preprint arXiv:1907.13487 ( 2019 ). Yang Liu, Samuel Albanie, Arsha Nagrani, and Andrew Zisserman. 2019. Use what you have: Video retrieval using representations from collaborative experts. arXiv preprint arXiv:1907.13487 (2019)."},{"key":"e_1_3_2_2_19_1","volume-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353","author":"Luo Huaishao","year":"2020","unstructured":"Huaishao Luo , Lei Ji , Botian Shi , Haoyang Huang , Nan Duan , Tianrui Li , Jason Li , Taroon Bharti , and Ming Zhou . 2020 . Univl: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020). Huaishao Luo, Lei Ji, Botian Shi, Haoyang Huang, Nan Duan, Tianrui Li, Jason Li, Taroon Bharti, and Ming Zhou. 2020. Univl: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)."},{"key":"e_1_3_2_2_20_1","volume-title":"Clip4clip: An empirical study of clip for end to end video clip retrieval. arXiv preprint arXiv:2104.08860","author":"Luo Huaishao","year":"2021","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. arXiv preprint arXiv:2104.08860 ( 2021 ). 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. arXiv preprint arXiv:2104.08860 (2021)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"e_1_3_2_2_23_1","volume-title":"Learning a text-video embedding from incomplete and heterogeneous data. arXiv preprint arXiv:1804.02516","author":"Miech Antoine","year":"2018","unstructured":"Antoine Miech , Ivan Laptev , and Josef Sivic . 2018. Learning a text-video embedding from incomplete and heterogeneous data. arXiv preprint arXiv:1804.02516 ( 2018 ). Antoine Miech, Ivan Laptev, and Josef Sivic. 2018. Learning a text-video embedding from incomplete and heterogeneous data. arXiv preprint arXiv:1804.02516 (2018)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"e_1_3_2_2_26_1","volume-title":"Im2text: Describing images using 1 million captioned photographs. Advances in neural information processing systems 24","author":"Ordonez Vicente","year":"2011","unstructured":"Vicente Ordonez , Girish Kulkarni , and Tamara Berg . 2011. Im2text: Describing images using 1 million captioned photographs. Advances in neural information processing systems 24 ( 2011 ), 1143--1151. Vicente Ordonez, Girish Kulkarni, and Tamara Berg. 2011. Im2text: Describing images using 1 million captioned photographs. Advances in neural information processing systems 24 (2011), 1143--1151."},{"key":"e_1_3_2_2_27_1","volume-title":"International Conference on Learning Representations.","author":"Patrick Mandela","year":"2020","unstructured":"Mandela Patrick , Po-Yao Huang , Yuki Asano , Florian Metze , Alexander G Hauptmann , Joao F Henriques , and Andrea Vedaldi . 2020 . Support-set bottlenecks for video-text representation learning . In International Conference on Learning Representations. Mandela Patrick, Po-Yao Huang, Yuki Asano, Florian Metze, Alexander G Hauptmann, Joao F Henriques, and Andrea Vedaldi. 2020. Support-set bottlenecks for video-text representation learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"e_1_3_2_2_29_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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. arXiv preprint arXiv:2103.00020 (2021). 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. arXiv preprint arXiv:2103.00020 (2021)."},{"key":"e_1_3_2_2_30_1","volume-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114","author":"Schuhmann Christoph","year":"2021","unstructured":"Christoph Schuhmann , Richard Vencu , Romain Beaumont , Robert Kaczmarczyk , Clayton Mullis , Aarush Katta , Theo Coombes , Jenia Jitsev , and Aran Komatsuzaki . 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 ( 2021 ). Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis, Aarush Katta, Theo Coombes, Jenia Jitsev, and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_2_33_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00365"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"e_1_3_2_2_38_1","volume-title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding. arXiv preprint arXiv:2109.14084","author":"Xu Hu","year":"2021","unstructured":"Hu Xu , Gargi Ghosh , Po-Yao Huang , Dmytro Okhonko , Armen Aghajanyan , and Florian Metze Luke Zettlemoyer Christoph Feichtenhofer . 2021. VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding. arXiv preprint arXiv:2109.14084 ( 2021 ). Hu Xu, Gargi Ghosh, Po-Yao Huang, Dmytro Okhonko, Armen Aghajanyan, and Florian Metze Luke Zettlemoyer Christoph Feichtenhofer. 2021. VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding. arXiv preprint arXiv:2109.14084 (2021)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"e_1_3_2_2_41_1","volume-title":"A graph-based relevance matching model for ad-hoc retrieval. arXiv preprint arXiv:2101.11873","author":"Zhang Yufeng","year":"2021","unstructured":"Yufeng Zhang , Jinghao Zhang , Zeyu Cui , Shu Wu , and Liang Wang . 2021. A graph-based relevance matching model for ad-hoc retrieval. arXiv preprint arXiv:2101.11873 ( 2021 ). Yufeng Zhang, Jinghao Zhang, Zeyu Cui, Shu Wu, and Liang Wang. 2021. A graph-based relevance matching model for ad-hoc retrieval. arXiv preprint arXiv:2101.11873 (2021)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Madrid Spain","acronym":"SIGIR '22","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531776","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3531776","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:25Z","timestamp":1750183825000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531776"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":42,"alternative-id":["10.1145\/3477495.3531776","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3531776","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]},"assertion":[{"value":"2022-07-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}