{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:44:54Z","timestamp":1787017494303,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.6190213"],"award-info":[{"award-number":["No.6190213"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China (key program)","award":["No.62232007"],"award-info":[{"award-number":["No.62232007"]}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["No.2022CFB060"],"award-info":[{"award-number":["No.2022CFB060"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3613440","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"1677-1688","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["CHAIN: Exploring Global-Local Spatio-Temporal Information for Improved Self-Supervised Video Hashing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1164-6360","authenticated-orcid":false,"given":"Rukai","family":"Wei","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1964-9278","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3464-1556","authenticated-orcid":false,"given":"Heng","family":"Cui","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9274-2807","authenticated-orcid":false,"given":"Yanzhao","family":"Xie","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2161-8796","authenticated-orcid":false,"given":"Ke","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"824","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 Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 813--824."},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020","volume":"1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event (Proceedings of Machine Learning Research, Vol. 119). PMLR, 1597--1607."},{"key":"e_1_3_2_2_4_1","volume-title":"Exploring Simple Siamese Representation Learning. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021","author":"Chen Xinlei","year":"2021","unstructured":"Xinlei Chen and Kaiming He. 2021. Exploring Simple Siamese Representation Learning. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021. Computer Vision Foundation \/ IEEE, 15750--15758."},{"key":"e_1_3_2_2_5_1","volume-title":"Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","author":"Courbariaux Matthieu","year":"2015","unstructured":"Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. 2015. BinaryConnect: Training Deep Neural Networks with binary weights during propagations. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, Corinna Cortes, Neil D. Lawrence, Daniel D. Lee, Masashi Sugiyama, and Roman Garnett (Eds.). 3123--3131."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548342"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_8_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). Association for Computational Linguistics, 4171--4186."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547976"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"e_1_3_2_2_11_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua 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 International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net."},{"key":"e_1_3_2_2_12_1","volume-title":"Clustering by passing messages between data points. science","author":"Frey Brendan J","year":"2007","unstructured":"Brendan J Frey and Delbert Dueck. 2007. Clustering by passing messages between data points. science, Vol. 315, 5814 (2007), 972--976."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995432"},{"key":"e_1_3_2_2_14_1","volume-title":"Zhaohan Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, R\u00e9mi Munos, and Michal Valko.","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill, Florian Strub, Florent Altch\u00e9, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo \u00c1 vila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, R\u00e9mi Munos, and Michal Valko. 2020. Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning. (2020)."},{"key":"e_1_3_2_2_15_1","volume-title":"Unsupervised Video Hashing with Multi-granularity Contextualization and Multi-structure Preservation. In MM '22: The 30th ACM International Conference on Multimedia","author":"Hao Yanbin","year":"2022","unstructured":"Yanbin Hao, Jingru Duan, Hao Zhang, Bin Zhu, Pengyuan Zhou, and Xiangnan He. 2022. Unsupervised Video Hashing with Multi-granularity Contextualization and Multi-structure Preservation. In MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10 - 14, 2022. ACM, 3754--3763."},{"key":"e_1_3_2_2_16_1","volume-title":"Momentum Contrast for Unsupervised Visual Representation Learning. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross B. Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. Computer Vision Foundation \/ IEEE, 9726--9735."},{"key":"e_1_3_2_2_17_1","volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016. IEEE Computer Society, 770--778."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_21_1","volume-title":"Towards the Generalization of Contrastive Self-Supervised Learning. In The Eleventh International Conference on Learning Representations, ICLR","author":"Huang Weiran","year":"2023","unstructured":"Weiran Huang, Mingyang Yi, Xuyang Zhao, and Zihao Jiang. 2023. Towards the Generalization of Contrastive Self-Supervised Learning. In The Eleventh International Conference on Learning Representations, ICLR 2023."},{"key":"e_1_3_2_2_22_1","volume-title":"Tel Aviv","volume":"727","author":"Jia Menglin","year":"2022","unstructured":"Menglin Jia, Luming Tang, Bor-Chun Chen, Claire Cardie, Serge J. Belongie, Bharath Hariharan, and Ser-Nam Lim. 2022. Visual Prompt Tuning. In Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXIII (Lecture Notes in Computer Science, Vol. 13693), Shai Avidan, Gabriel J. Brostow, Moustapha Ciss\u00e9, Giovanni Maria Farinella, and Tal Hassner (Eds.). Springer, 709--727."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"e_1_3_2_2_24_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.)."},{"key":"e_1_3_2_2_25_1","volume-title":"Video Contrastive Learning with Global Context. In IEEE\/CVF International Conference on Computer Vision Workshops, ICCVW 2021","author":"Kuang Haofei","year":"2021","unstructured":"Haofei Kuang, Yi Zhu, Zhi Zhang, Xinyu Li, Joseph Tighe, S\u00f6 ren Schwertfeger, Cyrill Stachniss, and Mu Li. 2021. Video Contrastive Learning with Global Context. In IEEE\/CVF International Conference on Computer Vision Workshops, ICCVW 2021, Montreal, BC, Canada, October 11-17, 2021. IEEE, 3188."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00295"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133030"},{"key":"e_1_3_2_2_31_1","volume-title":"Prototypical Contrastive Learning of Unsupervised Representations. In International Conference on Learning Representations, ICLR","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Pan Zhou, Caiming Xiong, and Steven Hoi. 2021b. Prototypical Contrastive Learning of Unsupervised Representations. In International Conference on Learning Representations, ICLR 2021."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548431"},{"key":"e_1_3_2_2_33_1","volume-title":"Neighborhood Preserving Hashing for Scalable Video Retrieval. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019","author":"Li Shuyan","year":"2019","unstructured":"Shuyan Li, Zhixiang Chen, Jiwen Lu, Xiu Li, and Jie Zhou. 2019. Neighborhood Preserving Hashing for Scalable Video Retrieval. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019. IEEE, 8211--8220."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01334"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16296"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298862"},{"key":"e_1_3_2_2_37_1","volume-title":"Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training. CoRR","author":"Luo Dezhao","year":"2023","unstructured":"Dezhao Luo, Jiabo Huang, Shaogang Gong, Hailin Jin, and Yang Liu. 2023. Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training. CoRR, Vol. abs\/2303.00040 (2023)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475570"},{"key":"e_1_3_2_2_39_1","volume-title":"Amsterdam, The Netherlands","volume":"544","author":"Misra Ishan","year":"2016","unstructured":"Ishan Misra, C. Lawrence Zitnick, and Martial Hebert. 016. Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification. In Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part I (Lecture Notes in Computer Science, Vol. 9905), Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.). Springer, 527--544."},{"key":"e_1_3_2_2_40_1","volume-title":"VideoMoCo: Contrastive Video Representation Learning With Temporally Adversarial Examples. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021","author":"Pan Tian","year":"2021","unstructured":"Tian Pan, Yibing Song, Tianyu Yang, Wenhao Jiang, and Wei Liu. 2021. VideoMoCo: Contrastive Video Representation Learning With Temporally Adversarial Examples. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021. Computer Vision Foundation \/ IEEE, 11205--11214."},{"key":"e_1_3_2_2_41_1","volume-title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning. CoRR","author":"Piergiovanni AJ","year":"2022","unstructured":"AJ Piergiovanni, Weicheng Kuo, and Anelia Angelova. 2022. Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning. CoRR, Vol. abs\/2212.03229 (2022)."},{"key":"e_1_3_2_2_42_1","volume-title":"Spatiotemporal Contrastive Video Representation Learning. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021","author":"Qian Rui","year":"2021","unstructured":"Rui Qian, Tianjian Meng, Boqing Gong, Ming-Hsuan Yang, Huisheng Wang, Serge J. Belongie, and Yin Cui. 2021. Spatiotemporal Contrastive Video Representation Learning. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021. Computer Vision Foundation \/ IEEE, 6964--6974."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/133"},{"key":"e_1_3_2_2_44_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","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), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763."},{"key":"e_1_3_2_2_45_1","volume-title":"Self-supervised Video Transformer. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Ranasinghe Kanchana","year":"2022","unstructured":"Kanchana Ranasinghe, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan, and Michael S. Ryoo. 2022. Self-supervised Video Transformer. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 2864--2874."},{"key":"e_1_3_2_2_46_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. (2015)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072354"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072354"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2814344"},{"key":"e_1_3_2_2_50_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. CoRR, Vol. abs\/1212.0402 (2012)."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547876"},{"key":"e_1_3_2_2_52_1","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Tolstikhin Ilya O.","year":"2021","unstructured":"Ilya O. Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, Mario Lucic, and Alexey Dosovitskiy. 2021. MLP-Mixer: An all-MLP Architecture for Vision. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual. 24261--24272."},{"key":"e_1_3_2_2_53_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 E. Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research, Vol. 9 (2008), 2579--2605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_54_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."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25373"},{"key":"e_1_3_2_2_56_1","volume-title":"CRIS: CLIP-Driven Referring Image Segmentation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Wang Zhaoqing","year":"2022","unstructured":"Zhaoqing Wang, Yu Lu, Qiang Li, Xunqiang Tao, Yandong Guo, Mingming Gong, and Tongliang Liu. 2022. CRIS: CLIP-Driven Referring Image Segmentation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 11676--11685."},{"key":"e_1_3_2_2_57_1","volume-title":"Spectral Hashing. In Proceedings of the 21st International Conference on Neural Information Processing Systems","author":"Weiss Yair","year":"2008","unstructured":"Yair Weiss, Antonio Torralba, and Rob Fergus. 2008. Spectral Hashing. In Proceedings of the 21st International Conference on Neural Information Processing Systems (Vancouver, British Columbia, Canada) (NIPS'08). Curran Associates Inc., Red Hook, NY, USA, 1753--1760."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17274"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547935"},{"key":"e_1_3_2_2_60_1","volume-title":"Central Similarity Quantization for Efficient Image and Video Retrieval. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Yuan Li","year":"2020","unstructured":"Li Yuan, Tao Wang, Xiaopeng Zhang, Francis E. H. Tay, Zequn Jie, Wei Liu, and Jiashi Feng. 2020. Central Similarity Quantization for Efficient Image and Video Retrieval. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. Computer Vision Foundation \/ IEEE, 3080--3089."},{"key":"e_1_3_2_2_61_1","volume-title":"Time Is MattEr: Temporal Self-supervision for Video Transformers. In International Conference on Machine Learning, ICML 2022","volume":"25816","author":"Yun Sukmin","year":"2022","unstructured":"Sukmin Yun, Jaehyung Kim, Dongyoon Han, Hwanjun Song, Jung-Woo Ha, and Jinwoo Shin. 2022. Time Is MattEr: Temporal Self-supervision for Video Transformers. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 25804--25816."},{"key":"e_1_3_2_2_62_1","volume-title":"Recurrent Neural Network Regularization. CoRR","author":"Zaremba Wojciech","year":"2014","unstructured":"Wojciech Zaremba, Ilya Sutskever, and Oriol Vinyals. 2014. Recurrent Neural Network Regularization. CoRR, Vol. abs\/1409.2329 (2014). [arXiv]1409.2329"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964308"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016236"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613440","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3613440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:44Z","timestamp":1755820844000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613440"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":64,"alternative-id":["10.1145\/3581783.3613440","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3613440","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}