{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T09:56:28Z","timestamp":1773741388806,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"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":["61702078"],"award-info":[{"award-number":["61702078"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548046","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:46Z","timestamp":1665416566000},"page":"4779-4788","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Fine-grained Action Recognition with Robust Motion Representation Decoupling and Concentration"],"prefix":"10.1145","author":[{"given":"Baoli","family":"Sun","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinchen","family":"Ye","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiantian","family":"Yan","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihui","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haojie","family":"Li","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"MultiModal Language Modelling on Knowledge Graphs for Deep Video Understanding. In MM '21: ACM Multimedia, October. 4868--4872","author":"Anand Vishal","year":"2021","unstructured":"Vishal Anand , Raksha Ramesh , Boshen Jin , Ziyin Wang , Xiaoxiao Lei , and Ching-Yung Lin . 2021 . MultiModal Language Modelling on Knowledge Graphs for Deep Video Understanding. In MM '21: ACM Multimedia, October. 4868--4872 . Vishal Anand, Raksha Ramesh, Boshen Jin, Ziyin Wang, Xiaoxiao Lei, and Ching-Yung Lin. 2021. MultiModal Language Modelling on Knowledge Graphs for Deep Video Understanding. In MM '21: ACM Multimedia, October. 4868--4872."},{"key":"e_1_3_2_2_2_1","volume-title":"Long Short View Feature Decomposition via Contrastive Video Representation Learning","author":"Behrmann Nadine","unstructured":"Nadine Behrmann , Mohsen Fayyaz , Juergen Gall , and Mehdi Noroozi . 2021. Long Short View Feature Decomposition via Contrastive Video Representation Learning . In IEEE ICCV. 9244--9253. Nadine Behrmann, Mohsen Fayyaz, Juergen Gall, and Mehdi Noroozi. 2021. Long Short View Feature Decomposition via Contrastive Video Representation Learning. In IEEE ICCV. 9244--9253."},{"key":"e_1_3_2_2_3_1","volume-title":"Action Recognition? A New Model and the Kinetics Dataset","author":"Carreira Jo","unstructured":"Jo a o Carreira and Andrew Zisserman . 2017. Quo Vadis , Action Recognition? A New Model and the Kinetics Dataset . In IEEE CVPR , July. 4724--4733. Jo a o Carreira and Andrew Zisserman. 2017. Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. In IEEE CVPR, July. 4724--4733."},{"key":"e_1_3_2_2_4_1","first-page":"1597","article-title":"A Simple Framework for Contrastive Learning of Visual Representations","volume":"119","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 ICML , Vol. 119. 1597 -- 1607 . Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In ICML, Vol. 119. 1597--1607.","journal-title":"ICML"},{"key":"e_1_3_2_2_5_1","volume-title":"Yu-Chiang Frank Wang, and Jia-Bin Huang","author":"Chen Wei-Yu","year":"2019","unstructured":"Wei-Yu Chen , Yen-Cheng Liu , Zsolt Kira , Yu-Chiang Frank Wang, and Jia-Bin Huang . 2019 . A Closer Look at Few-shot Classification. In ICLR , May. Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia-Bin Huang. 2019. A Closer Look at Few-shot Classification. In ICLR, May."},{"key":"e_1_3_2_2_6_1","volume-title":"Exploring Simple Siamese Representation Learning","author":"Chen Xinlei","unstructured":"Xinlei Chen and Kaiming He. 2021. Exploring Simple Siamese Representation Learning . In IEEE CVPR. 15750--15758. Xinlei Chen and Kaiming He. 2021. Exploring Simple Siamese Representation Learning. In IEEE CVPR. 15750--15758."},{"key":"e_1_3_2_2_7_1","volume-title":"CaFGraph: Context-aware Facial Multi-graph Representation for Facial Action Unit Recognition. In MM '21: ACM Multimedia, October. 1029--1037","author":"Chen Yingjie","year":"2021","unstructured":"Yingjie Chen , Diqi Chen , Yizhou Wang , Tao Wang , and Yun Liang . 2021 . CaFGraph: Context-aware Facial Multi-graph Representation for Facial Action Unit Recognition. In MM '21: ACM Multimedia, October. 1029--1037 . Yingjie Chen, Diqi Chen, Yizhou Wang, Tao Wang, and Yun Liang. 2021. CaFGraph: Context-aware Facial Multi-graph Representation for Facial Action Unit Recognition. In MM '21: ACM Multimedia, October. 1029--1037."},{"key":"e_1_3_2_2_8_1","volume-title":"Mamshad Nayeem Rizve, and Mubarak Shah","author":"Dave Ishan R.","year":"2021","unstructured":"Ishan R. Dave , Rohit Gupta , Mamshad Nayeem Rizve, and Mubarak Shah . 2021 . TCLR : Temporal Contrastive Learning for Video Representation. CoRR ( 2021). https:\/\/arxiv.org\/abs\/2101.07974 Ishan R. Dave, Rohit Gupta, Mamshad Nayeem Rizve, and Mubarak Shah. 2021. TCLR: Temporal Contrastive Learning for Video Representation. CoRR (2021). https:\/\/arxiv.org\/abs\/2101.07974"},{"key":"e_1_3_2_2_9_1","volume-title":"Rahman Yousefzadeh, Juergen Gall, and Luc Van Gool.","author":"Diba Ali","year":"2018","unstructured":"Ali Diba , Mohsen Fayyaz , Vivek Sharma , Mohammad Mahdi Arzani , Rahman Yousefzadeh, Juergen Gall, and Luc Van Gool. 2018 . Spatio-temporal Channel Correlation Networks for Action Classification. In ECCV , September. 299--315. Ali Diba, Mohsen Fayyaz, Vivek Sharma, Mohammad Mahdi Arzani, Rahman Yousefzadeh, Juergen Gall, and Luc Van Gool. 2018. Spatio-temporal Channel Correlation Networks for Action Classification. In ECCV, September. 299--315."},{"key":"e_1_3_2_2_10_1","volume-title":"Mohammad Mahdi Arzani, Rahman Yousefzadeh, and Luc Van Gool.","author":"Diba Ali","year":"2017","unstructured":"Ali Diba , Mohsen Fayyaz , Vivek Sharma , Amir Hossein Karami , Mohammad Mahdi Arzani, Rahman Yousefzadeh, and Luc Van Gool. 2017 . Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification. CoRR , Vol. abs\/ 1711 .08200 (2017). Ali Diba, Mohsen Fayyaz, Vivek Sharma, Amir Hossein Karami, Mohammad Mahdi Arzani, Rahman Yousefzadeh, and Luc Van Gool. 2017. Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification. CoRR , Vol. abs\/1711.08200 (2017)."},{"key":"e_1_3_2_2_11_1","volume-title":"Efros","author":"Doersch Carl","year":"2015","unstructured":"Carl Doersch , Abhinav Gupta , and Alexei A . Efros . 2015 . Unsupervised Visual Representation Learning by Context Prediction. In IEEE ICCV. 1422--1430. Carl Doersch, Abhinav Gupta, and Alexei A. Efros. 2015. Unsupervised Visual Representation Learning by Context Prediction. In IEEE ICCV. 1422--1430."},{"key":"e_1_3_2_2_12_1","volume-title":"SlowFast Networks for Video Recognition","author":"Feichtenhofer Christoph","unstructured":"Christoph Feichtenhofer , Haoqi Fan , Jitendra Malik , and Kaiming He. 2019. SlowFast Networks for Video Recognition . In IEEE ICCV , October. 6201--6210. Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He. 2019. SlowFast Networks for Video Recognition. In IEEE ICCV, October. 6201--6210."},{"key":"e_1_3_2_2_13_1","volume-title":"Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition","author":"Ghadiyaram Deepti","year":"2046","unstructured":"Deepti Ghadiyaram , Du Tran , and Dhruv Mahajan . 2019. Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition . In IEEE CVPR , June. 1 2046 --12055. Deepti Ghadiyaram, Du Tran, and Dhruv Mahajan. 2019. Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition. In IEEE CVPR, June. 12046--12055."},{"key":"e_1_3_2_2_14_1","first-page":"5843","article-title":"The \"Something Something","author":"Goyal Raghav","year":"2017","unstructured":"Raghav Goyal , Samira Ebrahimi Kahou , Vincent Michalski , Joanna Materzynska , Susanne Westphal , Heuna Kim , Valentin Haenel , Ingo Fr\u00fc nd, Peter Yianilos , Moritz Mueller-Freitag , Florian Hoppe , Christian Thurau , Ingo Bax , and Roland Memisevic . 2017 . The \"Something Something \" Video Database for Learning and Evaluating Visual Common Sense. In IEEE ICCV , October . 5843 -- 5851 . Raghav Goyal, Samira Ebrahimi Kahou, Vincent Michalski, Joanna Materzynska, Susanne Westphal, Heuna Kim, Valentin Haenel, Ingo Fr\u00fc nd, Peter Yianilos, Moritz Mueller-Freitag, Florian Hoppe, Christian Thurau, Ingo Bax, and Roland Memisevic. 2017. The \"Something Something\" Video Database for Learning and Evaluating Visual Common Sense. In IEEE ICCV, October. 5843--5851.","journal-title":"In IEEE ICCV"},{"key":"e_1_3_2_2_15_1","volume-title":"Zhaohan Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, R\u00e9 mi 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\u00e9 mi Munos, and Michal Valko. 2020 . Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning. In NeurIPS. 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\u00e9 mi Munos, and Michal Valko. 2020. Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning. In NeurIPS."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Dongliang He Zhichao Zhou Chuang Gan Fu Li Xiao Liu Yandong Li Limin Wang and Shilei Wen. 2019. StNet: Local and Global Spatial-Temporal Modeling for Action Recognition. In AAAI February. 8401--8408.  Dongliang He Zhichao Zhou Chuang Gan Fu Li Xiao Liu Yandong Li Limin Wang and Shilei Wen. 2019. StNet: Local and Global Spatial-Temporal Modeling for Action Recognition. In AAAI February. 8401--8408.","DOI":"10.1609\/aaai.v33i01.33018401"},{"key":"e_1_3_2_2_17_1","volume-title":"Girshick","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 IEEE CVPR. 9726--9735. Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross B. Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In IEEE CVPR. 9726--9735."},{"key":"e_1_3_2_2_18_1","volume-title":"ActivityNet: A large-scale video benchmark for human activity understanding","author":"Heilbron Fabian Caba","unstructured":"Fabian Caba Heilbron , Victor Escorcia , Bernard Ghanem , and Juan Carlos Niebles . 2015. ActivityNet: A large-scale video benchmark for human activity understanding . In IEEE CVPR , June. 961--970. Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem, and Juan Carlos Niebles. 2015. ActivityNet: A large-scale video benchmark for human activity understanding. In IEEE CVPR, June. 961--970."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105520"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2019.2923209"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2946469"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"e_1_3_2_2_23_1","volume-title":"Hauptmann","author":"Kang Guoliang","year":"2020","unstructured":"Guoliang Kang , Yunchao Wei , Yi Yang , Yueting Zhuang , and Alexander G . Hauptmann . 2020 . Pixel-Level Cycle Association : A New Perspective for Domain Adaptive Semantic Segmentation. In NeurIPS, December 6--12, virtual. Guoliang Kang, Yunchao Wei, Yi Yang, Yueting Zhuang, and Alexander G. Hauptmann. 2020. Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation. In NeurIPS, December 6--12, virtual."},{"key":"e_1_3_2_2_24_1","volume-title":"Kipf and Max Welling","author":"Thomas","year":"2017","unstructured":"Thomas N. Kipf and Max Welling . 2017 . Semi-Supervised Classification with Graph Convolutional Networks. In ICLR , April. Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR, April."},{"key":"e_1_3_2_2_25_1","volume-title":"Ali Bilgin Arslan, and Thomas Serre","author":"Kuehne Hilde","year":"2014","unstructured":"Hilde Kuehne , Ali Bilgin Arslan, and Thomas Serre . 2014 . The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities. In IEEE CVPR , June. 780--787. Hilde Kuehne, Ali Bilgin Arslan, and Thomas Serre. 2014. The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities. In IEEE CVPR, June. 780--787."},{"key":"e_1_3_2_2_26_1","volume-title":"Austin Reiter, and Gregory D. Hager","author":"Lea Colin","year":"2017","unstructured":"Colin Lea , Michael D. Flynn , Ren\u00e9 Vidal , Austin Reiter, and Gregory D. Hager . 2017 . Temporal Convolutional Networks for Action Segmentation and Detection. In IEEE CVPR , July. 1003--1012. Colin Lea, Michael D. Flynn, Ren\u00e9 Vidal, Austin Reiter, and Gregory D. Hager. 2017. Temporal Convolutional Networks for Action Segmentation and Detection. In IEEE CVPR, July. 1003--1012."},{"key":"e_1_3_2_2_27_1","volume-title":"Temporal Deformable Residual Networks for Action Segmentation in Videos","author":"Lei Peng","unstructured":"Peng Lei and Sinisa Todorovic . 2018. Temporal Deformable Residual Networks for Action Segmentation in Videos . In IEEE CVPR , June. 6742--6751. Peng Lei and Sinisa Todorovic. 2018. Temporal Deformable Residual Networks for Action Segmentation in Videos. In IEEE CVPR, June. 6742--6751."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Xiangpeng Li Jingkuan Song Lianli Gao Xianglong Liu Wenbing Huang Xiangnan He and Chuang Gan. 2019. Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering. In AAAI February. 8658--8665.  Xiangpeng Li Jingkuan Song Lianli Gao Xianglong Liu Wenbing Huang Xiangnan He and Chuang Gan. 2019. Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering. In AAAI February. 8658--8665.","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"e_1_3_2_2_29_1","volume-title":"TEA: Temporal Excitation and Aggregation for Action Recognition","author":"Li Yan","year":"2020","unstructured":"Yan Li , Bin Ji , Xintian Shi , Jianguo Zhang , Bin Kang , and Limin Wang . 2020 . TEA: Temporal Excitation and Aggregation for Action Recognition . In IEEE CVPR , June. 906--915. Yan Li, Bin Ji, Xintian Shi, Jianguo Zhang, Bin Kang, and Limin Wang. 2020. TEA: Temporal Excitation and Aggregation for Action Recognition. In IEEE CVPR, June. 906--915."},{"key":"e_1_3_2_2_30_1","volume-title":"RESOUND: Towards Action Recognition Without Representation Bias. In ECCV, September. 520--535.","author":"Li Yingwei","year":"2018","unstructured":"Yingwei Li , Yi Li , and Nuno Vasconcelos . 2018 b. RESOUND: Towards Action Recognition Without Representation Bias. In ECCV, September. 520--535. Yingwei Li, Yi Li, and Nuno Vasconcelos. 2018b. RESOUND: Towards Action Recognition Without Representation Bias. In ECCV, September. 520--535."},{"key":"e_1_3_2_2_31_1","volume-title":"Snoek","author":"Li Zhenyang","year":"2018","unstructured":"Zhenyang Li , Kirill Gavrilyuk , Efstratios Gavves , Mihir Jain , and Cees G. M . Snoek . 2018 a. VideoLSTM convolves, attends and flows for action recognition. Comput. Vis. Image Underst . (2018), 41--50. Zhenyang Li, Kirill Gavrilyuk, Efstratios Gavves, Mihir Jain, and Cees G. M. Snoek. 2018a. VideoLSTM convolves, attends and flows for action recognition. Comput. Vis. Image Underst. (2018), 41--50."},{"key":"e_1_3_2_2_32_1","volume-title":"TSM: Temporal Shift Module for Efficient Video Understanding","author":"Lin Ji","year":"2019","unstructured":"Ji Lin , Chuang Gan , and Song Han . 2019 . TSM: Temporal Shift Module for Efficient Video Understanding . In IEEE ICCV , October. 7082--7092. Ji Lin, Chuang Gan, and Song Han. 2019. TSM: Temporal Shift Module for Efficient Video Understanding. In IEEE ICCV, October. 7082--7092."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416298"},{"key":"e_1_3_2_2_34_1","volume-title":"Yuille","author":"Luo Chenxu","year":"2019","unstructured":"Chenxu Luo and Alan L . Yuille . 2019 . Grouped Spatial-Temporal Aggregation for Efficient Action Recognition . In IEEE ICCV, October. 5511--5520. Chenxu Luo and Alan L. Yuille. 2019. Grouped Spatial-Temporal Aggregation for Efficient Action Recognition. In IEEE ICCV, October. 5511--5520."},{"key":"e_1_3_2_2_35_1","volume-title":"VideoMoCo: Contrastive Video Representation Learning With Temporally Adversarial Examples","author":"Pan Tian","unstructured":"Tian Pan , Yibing Song , Tianyu Yang , Wenhao Jiang , and Wei Liu . 2021. VideoMoCo: Contrastive Video Representation Learning With Temporally Adversarial Examples . In IEEE CVPR. 11205--11214. Tian Pan, Yibing Song, Tianyu Yang, Wenhao Jiang, and Wei Liu. 2021. VideoMoCo: Contrastive Video Representation Learning With Temporally Adversarial Examples. In IEEE CVPR. 11205--11214."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413910"},{"key":"e_1_3_2_2_37_1","volume-title":"Enhancing Self-Supervised Video Representation Learning via Multi-Level Feature Optimization","author":"Ding Shuangrui","unstructured":"Rui Qian, Yuxi Li, Huabin Liu, John See, Shuangrui Ding , Xian Liu , Dian Li , and Weiyao Lin . 2021a. Enhancing Self-Supervised Video Representation Learning via Multi-Level Feature Optimization . In IEEE ICCV. 7990--8001. Rui Qian, Yuxi Li, Huabin Liu, John See, Shuangrui Ding, Xian Liu, Dian Li, and Weiyao Lin. 2021a. Enhancing Self-Supervised Video Representation Learning via Multi-Level Feature Optimization. In IEEE ICCV. 7990--8001."},{"key":"e_1_3_2_2_38_1","volume-title":"Spatiotemporal Contrastive Video Representation Learning","author":"Qian Rui","unstructured":"Rui Qian , Tianjian Meng , Boqing Gong , Ming-Hsuan Yang , Huisheng Wang , Serge Belongie , and Yin Cui . 2021b. Spatiotemporal Contrastive Video Representation Learning . In IEEE CVPR. 6964--6974. Rui Qian, Tianjian Meng, Boqing Gong, Ming-Hsuan Yang, Huisheng Wang, Serge Belongie, and Yin Cui. 2021b. Spatiotemporal Contrastive Video Representation Learning. In IEEE CVPR. 6964--6974."},{"key":"e_1_3_2_2_39_1","volume-title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","author":"Qiu Zhaofan","unstructured":"Zhaofan Qiu , Ting Yao , and Tao Mei . 2017. Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks . In IEEE ICCV , October. 5534--5542. Zhaofan Qiu, Ting Yao, and Tao Mei. 2017. Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks. In IEEE ICCV, October. 5534--5542."},{"key":"e_1_3_2_2_40_1","volume-title":"Time-Contrastive Networks: Self-Supervised Learning from Video","author":"Sermanet Pierre","unstructured":"Pierre Sermanet , Corey Lynch , Yevgen Chebotar , Jasmine Hsu , Eric Jang , Stefan Schaal , and Sergey Levine . 2018. Time-Contrastive Networks: Self-Supervised Learning from Video . In IEEE ICRA. 1134--1141. Pierre Sermanet, Corey Lynch, Yevgen Chebotar, Jasmine Hsu, Eric Jang, Stefan Schaal, and Sergey Levine. 2018. Time-Contrastive Networks: Self-Supervised Learning from Video. In IEEE ICRA. 1134--1141."},{"key":"e_1_3_2_2_41_1","volume-title":"FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding","author":"Shao Dian","unstructured":"Dian Shao , Yue Zhao , Bo Dai , and Dahua Lin . 2020a. FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding . In IEEE CVPR , June. 2613--2622. Dian Shao, Yue Zhao, Bo Dai, and Dahua Lin. 2020a. FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding. In IEEE CVPR, June. 2613--2622."},{"key":"e_1_3_2_2_42_1","volume-title":"Intra- and Inter-Action Understanding via Temporal Action Parsing","author":"Shao Dian","unstructured":"Dian Shao , Yue Zhao , Bo Dai , and Dahua Lin . 2020b. Intra- and Inter-Action Understanding via Temporal Action Parsing . In IEEE CVPR , June. 727--736. Dian Shao, Yue Zhao, Bo Dai, and Dahua Lin. 2020b. Intra- and Inter-Action Understanding via Temporal Action Parsing. In IEEE CVPR, June. 727--736."},{"key":"e_1_3_2_2_43_1","volume-title":"Kate Saenko, and Abir Das.","author":"Singh Ankit","year":"2021","unstructured":"Ankit Singh , Omprakash Chakraborty , Ashutosh Varshney , Rameswar Panda , Rog\u00e9 rio Feris , Kate Saenko, and Abir Das. 2021 . Semi-Supervised Action Recognition With Temporal Contrastive Learning. In IEEE CVPR , June. 10389--10399. Ankit Singh, Omprakash Chakraborty, Ashutosh Varshney, Rameswar Panda, Rog\u00e9 rio Feris, Kate Saenko, and Abir Das. 2021. Semi-Supervised Action Recognition With Temporal Contrastive Learning. In IEEE CVPR, June. 10389--10399."},{"key":"e_1_3_2_2_44_1","volume-title":"D3D: Distilled 3D Networks for Video Action Recognition","author":"Stroud Jonathan C.","unstructured":"Jonathan C. Stroud , David A. Ross , Chen Sun , Jia Deng , and Rahul Sukthankar . 2020. D3D: Distilled 3D Networks for Video Action Recognition . In IEEE WACV , March. 614--623. Jonathan C. Stroud, David A. Ross, Chen Sun, Jia Deng, and Rahul Sukthankar. 2020. D3D: Distilled 3D Networks for Video Action Recognition. In IEEE WACV, March. 614--623."},{"key":"e_1_3_2_2_45_1","volume-title":"Reproducibility Companion Paper: Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework. In MM '21: ACM Multimedia, October. 3630--3632","author":"Tao Li","year":"2021","unstructured":"Li Tao , Xueting Wang , Toshihiko Yamasaki , Jingjing Chen , and Steven Hicks . 2021 . Reproducibility Companion Paper: Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework. In MM '21: ACM Multimedia, October. 3630--3632 . Li Tao, Xueting Wang, Toshihiko Yamasaki, Jingjing Chen, and Steven Hicks. 2021. Reproducibility Companion Paper: Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework. In MM '21: ACM Multimedia, October. 3630--3632."},{"key":"e_1_3_2_2_46_1","volume-title":"Learning Spatiotemporal Features with 3D Convolutional Networks","author":"Tran Du","unstructured":"Du Tran , Lubomir D. Bourdev , Rob Fergus , Lorenzo Torresani , and Manohar Paluri . 2015. Learning Spatiotemporal Features with 3D Convolutional Networks . In IEEE ICCV , December. 4489--4497. Du Tran, Lubomir D. Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. 2015. Learning Spatiotemporal Features with 3D Convolutional Networks. In IEEE ICCV, December. 4489--4497."},{"key":"e_1_3_2_2_47_1","volume-title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","author":"Tran Du","unstructured":"Du Tran , Heng Wang , Lorenzo Torresani , Jamie Ray , Yann LeCun , and Manohar Paluri . 2018. A Closer Look at Spatiotemporal Convolutions for Action Recognition . In IEEE CVPR , June. 6450--6459. Du Tran, Heng Wang, Lorenzo Torresani, Jamie Ray, Yann LeCun, and Manohar Paluri. 2018. A Closer Look at Spatiotemporal Convolutions for Action Recognition. In IEEE CVPR, June. 6450--6459."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_2_50_1","volume-title":"Interactive Prototype Learning for Egocentric Action Recognition","author":"Wang Xiaohan","unstructured":"Xiaohan Wang , Linchao Zhu , Heng Wang , and Yi Yang . 2021b. Interactive Prototype Learning for Egocentric Action Recognition . In IEEE ICCV , October. 8148--8157. Xiaohan Wang, Linchao Zhu, Heng Wang, and Yi Yang. 2021b. Interactive Prototype Learning for Egocentric Action Recognition. In IEEE ICCV, October. 8148--8157."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350891"},{"key":"e_1_3_2_2_52_1","volume-title":"Unsupervised Feature Learning via Non-Parametric Instance Discrimination","author":"Wu Zhirong","unstructured":"Zhirong Wu , Yuanjun Xiong , Stella X. Yu , and Dahua Lin . 2018. Unsupervised Feature Learning via Non-Parametric Instance Discrimination . In IEEE CVPR , June. 3733--3742. Zhirong Wu, Yuanjun Xiong, Stella X. Yu, and Dahua Lin. 2018. Unsupervised Feature Learning via Non-Parametric Instance Discrimination. In IEEE CVPR, June. 3733--3742."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"crossref","unstructured":"Saining Xie Chen Sun Jonathan Huang Zhuowen Tu and Kevin Murphy. 2018. Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification. In ECCV September. 318--335.  Saining Xie Chen Sun Jonathan Huang Zhuowen Tu and Kevin Murphy. 2018. Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification. In ECCV September. 318--335.","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"e_1_3_2_2_54_1","volume-title":"Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning","author":"Xie Zhenda","year":"2021","unstructured":"Zhenda Xie , Yutong Lin , Zheng Zhang , Yue Cao , Stephen Lin , and Han Hu . 2021 . Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning . In IEEE CVPR. 16684--16693. Zhenda Xie, Yutong Lin, Zheng Zhang, Yue Cao, Stephen Lin, and Han Hu. 2021. Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning. In IEEE CVPR. 16684--16693."},{"key":"e_1_3_2_2_55_1","volume-title":"Temporal Query Networks for Fine-Grained Video Understanding","author":"Zhang Chuhan","unstructured":"Chuhan Zhang , Ankush Gupta , and Andrew Zisserman . 2021a. Temporal Query Networks for Fine-Grained Video Understanding . In IEEE CVPR , June. 4486--4496. Chuhan Zhang, Ankush Gupta, and Andrew Zisserman. 2021a. Temporal Query Networks for Fine-Grained Video Understanding. In IEEE CVPR, June. 4486--4496."},{"key":"e_1_3_2_2_56_1","volume-title":"Person Re-Identification Using Heterogeneous Local Graph Attention Networks","author":"Zhang Zhong","unstructured":"Zhong Zhang , Haijia Zhang , and Shuang Liu . 2021b. Person Re-Identification Using Heterogeneous Local Graph Attention Networks . In IEEE CVPR , June. 12136--12145. Zhong Zhang, Haijia Zhang, and Shuang Liu. 2021b. Person Re-Identification Using Heterogeneous Local Graph Attention Networks. In IEEE CVPR, June. 12136--12145."},{"key":"e_1_3_2_2_57_1","volume-title":"Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization","author":"Zhao Long","unstructured":"Long Zhao , Yuxiao Wang , Jiaping Zhao , Liangzhe Yuan , Jennifer J. Sun , Florian Schroff , Hartwig Adam , Xi Peng , Dimitris N. Metaxas , and Ting Liu . 2021. Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization . In IEEE CVPR , June. 12793--12802. Long Zhao, Yuxiao Wang, Jiaping Zhao, Liangzhe Yuan, Jennifer J. Sun, Florian Schroff, Hartwig Adam, Xi Peng, Dimitris N. Metaxas, and Ting Liu. 2021. Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization. In IEEE CVPR, June. 12793--12802."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"crossref","unstructured":"Bolei Zhou Alex Andonian Aude Oliva and Antonio Torralba. 2018. Temporal Relational Reasoning in Videos. In ECCV September. 831--846.  Bolei Zhou Alex Andonian Aude Oliva and Antonio Torralba. 2018. Temporal Relational Reasoning in Videos. In ECCV September. 831--846.","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"e_1_3_2_2_59_1","volume-title":"ECO: Efficient Convolutional Network for Online Video Understanding. In ECCV, September. 713--730.io","author":"Zolfaghari Mohammadreza","year":"2018","unstructured":"Mohammadreza Zolfaghari , Kamaljeet Singh , and Thomas Brox . 2018 . ECO: Efficient Convolutional Network for Online Video Understanding. In ECCV, September. 713--730.io Mohammadreza Zolfaghari, Kamaljeet Singh, and Thomas Brox. 2018. ECO: Efficient Convolutional Network for Online Video Understanding. In ECCV, September. 713--730.io"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548046","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:29Z","timestamp":1750186949000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548046"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":59,"alternative-id":["10.1145\/3503161.3548046","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548046","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}