{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:56:58Z","timestamp":1784300218557,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":69,"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"}],"funder":[{"name":"National Key R&D Program of China","award":["2020AAA0108800"],"award-info":[{"award-number":["2020AAA0108800"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,6]]},"DOI":"10.1145\/3477495.3531950","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:13Z","timestamp":1657206733000},"page":"970-981","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":130,"title":["CenterCLIP"],"prefix":"10.1145","author":[{"given":"Shuai","family":"Zhao","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linchao","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohan","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2007","author":"Arthur David","year":"2007","unstructured":"David Arthur and Sergei Vassilvitskii . 2007 . k-means++: the advantages of careful seeding . In Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2007 , New Orleans, Louisiana, USA , January 7-9, 2007, Nikhil Bansal, Kirk Pruhs, and Clifford Stein (Eds.). SIAM, 1027--1035. David Arthur and Sergei Vassilvitskii. 2007. k-means++: the advantages of careful seeding. In Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2007, New Orleans, Louisiana, USA, January 7-9, 2007, Nikhil Bansal, Kirk Pruhs, and Clifford Stein (Eds.). SIAM, 1027--1035."},{"key":"e_1_3_2_2_2_1","volume-title":"Frozen in time: A joint video and image encoder for end-to-end retrieval. arXiv preprint arXiv:2104.00650","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. arXiv preprint arXiv:2104.00650 ( 2021 ). 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. arXiv preprint arXiv:2104.00650 (2021)."},{"key":"e_1_3_2_2_3_1","volume-title":"Longformer: The long- document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy , Matthew E Peters , and Arman Cohan . 2020 . Longformer: The long- document transformer. arXiv preprint arXiv:2004.05150 (2020). Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long- document transformer. arXiv preprint arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_2_4_1","unstructured":"Rishi Bommasani Drew A Hudson Ehsan Adeli Russ Altman Simran Arora Sydney von Arx Michael S Bernstein Jeannette Bohg Antoine Bosselut Emma Brunskill etal 2021. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021).  Rishi Bommasani Drew A Hudson Ehsan Adeli Russ Altman Simran Arora Sydney von Arx Michael S Bernstein Jeannette Bohg Antoine Bosselut Emma Brunskill et al. 2021. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/cem.1122"},{"key":"e_1_3_2_2_6_1","volume-title":"Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS","author":"Cao Shuhao","year":"2021","unstructured":"Shuhao Cao . 2021 . Choose a Transformer: Fourier or Galerkin . In Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS 2021). arXiv:arXiv: 2105.14995 [cs.CL] Shuhao Cao. 2021. Choose a Transformer: Fourier or Galerkin. In Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS 2021). arXiv:arXiv: 2105.14995 [cs.CL]"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"key":"e_1_3_2_2_8_1","volume-title":"Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509","author":"Child Rewon","year":"2019","unstructured":"Rewon Child , Scott Gray , Alec Radford , and Ilya Sutskever . 2019. Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 ( 2019 ). Rewon Child, Scott Gray, Alec Radford, and Ilya Sutskever. 2019. Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)."},{"key":"e_1_3_2_2_9_1","unstructured":"Krzysztof Choromanski Valerii Likhosherstov David Dohan Xingyou Song Andreea Gane Tamas Sarlos Peter Hawkins Jared Davis Afroz Mohiuddin Lukasz Kaiser etal 2020. Rethinking attention with performers. arXiv preprint arXiv:2009.14794 (2020).  Krzysztof Choromanski Valerii Likhosherstov David Dohan Xingyou Song Andreea Gane Tamas Sarlos Peter Hawkins Jared Davis Afroz Mohiuddin Lukasz Kaiser et al. 2020. Rethinking attention with performers. arXiv preprint arXiv:2009.14794 (2020)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"e_1_3_2_2_11_1","volume-title":"ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy , Lucas Beyer , Alexander Kolesnikov , Dirk Weissenborn , Xi- aohua Zhai, Thomas Unterthiner , Mostafa Dehghani , Matthias Minderer , Georg Heigold , Sylvain Gelly , Jakob Uszkoreit , and Neil Houlsby . 2021 . An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th Interna- tional Conference on Learning Representations , ICLR 2021 , Virtual Event, Austria , May 3-7, 2021. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xi- aohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th Interna- tional Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021."},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 961--970","author":"Fabian Caba Heilbron Bernard Ghanem","year":"2015","unstructured":"Bernard Ghanem Fabian Caba Heilbron , Victor Escorcia and Juan Carlos Niebles . 2015 . ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 961--970 . Bernard Ghanem Fabian Caba Heilbron, Victor Escorcia and Juan Carlos Niebles. 2015. ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 961--970."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_2_2_14_1","volume-title":"Large Minibatch SGD: Training ImageNet in 1 Hour. CoRR abs\/1706.02677","author":"Goyal Priya","year":"2017","unstructured":"Priya Goyal , Piotr Doll\u00e1r , Ross B. Girshick , Pieter Noordhuis , Lukasz Wesolowski , Aapo Kyrola , Andrew Tulloch , Yangqing Jia , and Kaiming He. 2017. Accurate , Large Minibatch SGD: Training ImageNet in 1 Hour. CoRR abs\/1706.02677 ( 2017 ). arXiv:1706.02677 Priya Goyal, Piotr Doll\u00e1r, Ross B. Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, and Kaiming He. 2017. Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour. CoRR abs\/1706.02677 (2017). arXiv:1706.02677"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462927"},{"key":"e_1_3_2_2_16_1","volume-title":"Bag of Tricks for Image Classification with Convolutional Neural Networks. CoRR abs\/1812.01187","author":"He Tong","year":"2018","unstructured":"Tong He , Zhi Zhang , Hang Zhang , Zhongyue Zhang , Junyuan Xie , and Mu Li. 2018. Bag of Tricks for Image Classification with Convolutional Neural Networks. CoRR abs\/1812.01187 ( 2018 ). Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, and Mu Li. 2018. Bag of Tricks for Image Classification with Convolutional Neural Networks. CoRR abs\/1812.01187 (2018)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578775"},{"key":"e_1_3_2_2_18_1","unstructured":"Yuqi Huo Manli Zhang Guangzhen Liu Haoyu Lu Yizhao Gao Guoxing Yang Jingyuan Wen Heng Zhang Baogui Xu Weihao Zheng etal 2021. WenLan: Bridging vision and language by large-scale multi-modal pre-training. arXiv preprint arXiv:2103.06561 (2021).  Yuqi Huo Manli Zhang Guangzhen Liu Haoyu Lu Yizhao Gao Guoxing Yang Jingyuan Wen Heng Zhang Baogui Xu Weihao Zheng et al. 2021. WenLan: Bridging vision and language by large-scale multi-modal pre-training. arXiv preprint arXiv:2103.06561 (2021)."},{"key":"e_1_3_2_2_19_1","unstructured":"Andrew Jaegle Sebastian Borgeaud Jean-Baptiste Alayrac Carl Doersch Catalin Ionescu David Ding Skanda Koppula Daniel Zoran Andrew Brock Evan Shelhamer etal 2021. Perceiver io: A general architecture for structured inputs & outputs. arXiv preprint arXiv:2107.14795 (2021).  Andrew Jaegle Sebastian Borgeaud Jean-Baptiste Alayrac Carl Doersch Catalin Ionescu David Ding Skanda Koppula Daniel Zoran Andrew Brock Evan Shelhamer et al. 2021. Perceiver io: A general architecture for structured inputs & outputs. arXiv preprint arXiv:2107.14795 (2021)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"e_1_3_2_2_21_1","volume-title":"Scaling up visual and vision-language 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 vision-language 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 vision-language representation learning with noisy text supervision. arXiv preprint arXiv:2102.05918 (2021)."},{"key":"e_1_3_2_2_22_1","volume-title":"International Conference on Machine Learning. PMLR, 5156--5165","author":"Katharopoulos Angelos","year":"2020","unstructured":"Angelos Katharopoulos , Apoorv Vyas , Nikolaos Pappas , and Fran\u00e7ois Fleuret . 2020 . Transformers are rnns: Fast autoregressive transformers with linear atten- tion . In International Conference on Machine Learning. PMLR, 5156--5165 . Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas, and Fran\u00e7ois Fleuret. 2020. Transformers are rnns: Fast autoregressive transformers with linear atten- tion. In International Conference on Machine Learning. PMLR, 5156--5165."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/97.329844"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.20"},{"key":"e_1_3_2_2_25_1","volume-title":"Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451","author":"Kitaev Nikita","year":"2020","unstructured":"Nikita Kitaev , \"ukasz Kaiser, and Anselm Levskaya . 2020 . Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451 (2020). Nikita Kitaev, \"ukasz Kaiser, and Anselm Levskaya. 2020. Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451 (2020)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"e_1_3_2_2_28_1","volume-title":"Hero: Hierarchical encoder for video+ language omni-representation pre-training. arXiv preprint arXiv:2005.00200","author":"Li Linjie","year":"2020","unstructured":"Linjie Li , Yen-Chun Chen , Yu Cheng , Zhe Gan , Licheng Yu , and Jingjing Liu . 2020 . Hero: Hierarchical encoder for video+ language omni-representation pre-training. arXiv preprint arXiv:2005.00200 (2020). Linjie Li, Yen-Chun Chen, Yu Cheng, Zhe Gan, Licheng Yu, and Jingjing Liu. 2020. Hero: Hierarchical encoder for video+ language omni-representation pre-training. arXiv preprint arXiv:2005.00200 (2020)."},{"key":"e_1_3_2_2_29_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_30_1","volume-title":"Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030","author":"Liu Ze","year":"2021","unstructured":"Ze Liu , Yutong Lin , Yue Cao , Han Hu , Yixuan Wei , Zheng Zhang , Stephen Lin , and Baining Guo . 2021. Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 ( 2021 ). Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)."},{"key":"e_1_3_2_2_31_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2018","unstructured":"Ilya Loshchilov and Frank Hutter . 2018 . Decoupled Weight Decay Regularization. In International Conference on Learning Representations. Ilya Loshchilov and Frank Hutter. 2018. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_32_1","volume-title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval. CoRR abs\/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. CoRR abs\/2104.08860 ( 2021 ). arXiv:2104.08860 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:2104.08860"},{"key":"e_1_3_2_2_33_1","unstructured":"Paulius Micikevicius Sharan Narang Jonah Alben Gregory F. Diamos Erich Elsen David Garc\u00eda Boris Ginsburg Michael Houston Oleksii Kuchaiev Ganesh Venkatesh and Hao Wu. 2018. Mixed Precision Training. In ICLR.  Paulius Micikevicius Sharan Narang Jonah Alben Gregory F. Diamos Erich Elsen David Garc\u00eda Boris Ginsburg Michael Houston Oleksii Kuchaiev Ganesh Venkatesh and Hao Wu. 2018. Mixed Precision Training. In ICLR."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"e_1_3_2_2_36_1","unstructured":"Andrew Y. Ng Michael I. Jordan and Yair Weiss. 2001. On Spectral Clustering: Analysis and an algorithm. In ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS. 849--856.  Andrew Y. Ng Michael I. Jordan and Yair Weiss. 2001. On Spectral Clustering: Analysis and an algorithm. In ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS. 849--856."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"e_1_3_2_2_38_1","volume-title":"Support-set bottlenecks for video-text representation learning. arXiv preprint arXiv:2010.02824","author":"Patrick Mandela","year":"2020","unstructured":"Mandela Patrick , Po-Yao Huang , Yuki Asano , Florian Metze , Alexander Hauptmann , Joao Henriques , and Andrea Vedaldi . 2020. Support-set bottlenecks for video-text representation learning. arXiv preprint arXiv:2010.02824 ( 2020 ). Mandela Patrick, Po-Yao Huang, Yuki Asano, Florian Metze, Alexander Hauptmann, Joao Henriques, and Andrea Vedaldi. 2020. Support-set bottlenecks for video-text representation learning. arXiv preprint arXiv:2010.02824 (2020)."},{"key":"e_1_3_2_2_39_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. CoRR abs\/2103.00020 (2021). arXiv:2103.00020 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. CoRR abs\/2103.00020 (2021). arXiv:2103.00020"},{"key":"e_1_3_2_2_40_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever etal 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9.  Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_2_41_1","volume-title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification. arXiv preprint arXiv:2106.02034","author":"Rao Yongming","year":"2021","unstructured":"Yongming Rao , Wenliang Zhao , Benlin Liu , Jiwen Lu , Jie Zhou , and Cho-Jui Hsieh . 2021. DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification. arXiv preprint arXiv:2106.02034 ( 2021 ). Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou, and Cho-Jui Hsieh. 2021. DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification. arXiv preprint arXiv:2106.02034 (2021)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24947-6_17"},{"key":"e_1_3_2_2_43_1","volume-title":"Avlnet: Learning audio-visual language representations from instructional videos. arXiv preprint arXiv:2006.09199","author":"Rouditchenko Andrew","year":"2020","unstructured":"Andrew Rouditchenko , Angie Boggust , David Harwath , Brian Chen , Dhiraj Joshi , Samuel Thomas , Kartik Audhkhasi , Hilde Kuehne , Rameswar Panda , Rogerio Feris , 2020 . Avlnet: Learning audio-visual language representations from instructional videos. arXiv preprint arXiv:2006.09199 (2020). Andrew Rouditchenko, Angie Boggust, David Harwath, Brian Chen, Dhiraj Joshi, Samuel Thomas, Kartik Audhkhasi, Hilde Kuehne, Rameswar Panda, Rogerio Feris, et al. 2020. Avlnet: Learning audio-visual language representations from instructional videos. arXiv preprint arXiv:2006.09199 (2020)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"e_1_3_2_2_45_1","volume-title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? arXiv preprint arXiv:2106.11297","author":"Ryoo Michael S","year":"2021","unstructured":"Michael S Ryoo , AJ Piergiovanni , Anurag Arnab , Mostafa Dehghani , and Anelia Angelova . 2021. TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? arXiv preprint arXiv:2106.11297 ( 2021 ). Michael S Ryoo, AJ Piergiovanni, Anurag Arnab, Mostafa Dehghani, and Anelia Angelova. 2021. TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? arXiv preprint arXiv:2106.11297 (2021)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_2_47_1","volume-title":"Hao Tan, Mohit Bansal, Anna Rohrbach, Kai- Wei Chang, Zhewei Yao, and Kurt Keutzer.","author":"Shen Sheng","year":"2021","unstructured":"Sheng Shen , Liunian Harold Li , Hao Tan, Mohit Bansal, Anna Rohrbach, Kai- Wei Chang, Zhewei Yao, and Kurt Keutzer. 2021 . How Much Can CLIP Benefit Vision-and-Language Tasks ? arXiv preprint arXiv:2107.06383 (2021). Sheng Shen, Liunian Harold Li, Hao Tan, Mohit Bansal, Anna Rohrbach, Kai- Wei Chang, Zhewei Yao, and Kurt Keutzer. 2021. How Much Can CLIP Benefit Vision-and-Language Tasks? arXiv preprint arXiv:2107.06383 (2021)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/1367948.1367950"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_2_50_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton . 2008 . Visualizing Data using t-SNE . Journal of Machine Learning Research 9 , 86 (2008), 2579 -- 2605 . Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research 9, 86 (2008), 2579--2605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_51_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Vaswani Ashish","year":"2017","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 30: Annual Conference on Neural Information Processing Systems 2017 , December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 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 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998--6008."},{"key":"e_1_3_2_2_52_1","volume-title":"A tutorial on spectral clustering. Statistics and computing 17, 4","author":"Luxburg Ulrike Von","year":"2007","unstructured":"Ulrike Von Luxburg . 2007. A tutorial on spectral clustering. Statistics and computing 17, 4 ( 2007 ), 395--416. Ulrike Von Luxburg. 2007. A tutorial on spectral clustering. Statistics and computing 17, 4 (2007), 395--416."},{"key":"e_1_3_2_2_53_1","volume-title":"Efficient Video Transformers with Spatial-Temporal Token Selection. arXiv preprint arXiv:2111.11591","author":"Wang Junke","year":"2021","unstructured":"Junke Wang , Xitong Yang , Hengduo Li , Zuxuan Wu , and Yu-Gang Jiang . 2021. Efficient Video Transformers with Spatial-Temporal Token Selection. arXiv preprint arXiv:2111.11591 ( 2021 ). Junke Wang, Xitong Yang, Hengduo Li, Zuxuan Wu, and Yu-Gang Jiang. 2021. Efficient Video Transformers with Spatial-Temporal Token Selection. arXiv preprint arXiv:2111.11591 (2021)."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_2_55_1","volume-title":"Lin- former: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768","author":"Wang Sinong","year":"2020","unstructured":"Sinong Wang , Belinda Z Li , Madian Khabsa , Han Fang , and Hao Ma. 2020. Lin- former: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768 ( 2020 ). Sinong Wang, Belinda Z Li, Madian Khabsa, Han Fang, and Hao Ma. 2020. Lin- former: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"e_1_3_2_2_57_1","volume-title":"Visual transformers: Token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677","author":"Wu Bichen","year":"2020","unstructured":"Bichen Wu , Chenfeng Xu , Xiaoliang Dai , Alvin Wan , Peizhao Zhang , Zhicheng Yan , Masayoshi Tomizuka , Joseph Gonzalez , Kurt Keutzer , and Peter Vajda . 2020. Visual transformers: Token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677 ( 2020 ). Bichen Wu, Chenfeng Xu, Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Zhicheng Yan, Masayoshi Tomizuka, Joseph Gonzalez, Kurt Keutzer, and Peter Vajda. 2020. Visual transformers: Token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677 (2020)."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"e_1_3_2_2_59_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 , Florian Metze , Luke Zettlemoyer , and 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, Florian Metze, Luke Zettlemoyer, and 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_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_2_61_1","volume-title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer. arXiv preprint arXiv:2112.07658","author":"Yin Hongxu","year":"2021","unstructured":"Hongxu Yin , Arash Vahdat , Jose Alvarez , Arun Mallya , Jan Kautz , and Pavlo Molchanov . 2021. AdaViT: Adaptive Tokens for Efficient Vision Transformer. arXiv preprint arXiv:2112.07658 ( 2021 ). Hongxu Yin, Arash Vahdat, Jose Alvarez, Arun Mallya, Jan Kautz, and Pavlo Molchanov. 2021. AdaViT: Adaptive Tokens for Efficient Vision Transformer. arXiv preprint arXiv:2112.07658 (2021)."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"e_1_3_2_2_65_1","volume-title":"Florence: A New Foundation Model for Computer Vision. arXiv preprint arXiv:2111.11432","author":"Yuan Lu","year":"2021","unstructured":"Lu Yuan , Dongdong Chen , Yi-Ling Chen , Noel Codella , Xiyang Dai , Jianfeng Gao , Houdong Hu , Xuedong Huang , Boxin Li , Chunyuan Li , 2021 . Florence: A New Foundation Model for Computer Vision. arXiv preprint arXiv:2111.11432 (2021). Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, et al. 2021. Florence: A New Foundation Model for Computer Vision. arXiv preprint arXiv:2111.11432 (2021)."},{"key":"e_1_3_2_2_66_1","volume-title":"30th British Machine Vision Conference 2019, BMVC 2019","author":"Zhai Andrew","year":"2019","unstructured":"Andrew Zhai and Hao-Yu Wu . 2019 . Classification is a Strong Baseline for Deep Metric Learning . In 30th British Machine Vision Conference 2019, BMVC 2019 , Cardiff, UK , September 9-12, 2019. 91. Andrew Zhai and Hao-Yu Wu. 2019. Classification is a Strong Baseline for Deep Metric Learning. In 30th British Machine Vision Conference 2019, BMVC 2019, Cardiff, UK, September 9-12, 2019. 91."},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475272"},{"key":"e_1_3_2_2_69_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\/3477495.3531950","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3531950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:19Z","timestamp":1750183819000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531950"}},"subtitle":["Token Clustering for Efficient Text-Video Retrieval"],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":69,"alternative-id":["10.1145\/3477495.3531950","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3531950","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"}}]}}