{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T19:10:12Z","timestamp":1768677012683,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":60,"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":[{"name":"National Natural Science Foundation of China","award":["62101524"],"award-info":[{"award-number":["62101524"]}]},{"name":"The University Synergy Innovation Program of Anhui Province","award":["No. GXXT-2021-009"],"award-info":[{"award-number":["No. GXXT-2021-009"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1406703"],"award-info":[{"award-number":["2020YFB1406703"]}],"id":[{"id":"10.13039\/501100012166","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\/3503161.3547841","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"5880-5891","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Hierarchical Hourglass Convolutional Network for Efficient Video Classification"],"prefix":"10.1145","author":[{"given":"Yi","family":"Tan","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbin","family":"Hao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_2_2_1","volume-title":"International Conference on Machine Learning. PMLR, 813--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 International Conference on Machine Learning. PMLR, 813--824 . Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is Space-Time Attention All You Need for Video Understanding?. In International Conference on Machine Learning. PMLR, 813--824."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01757"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_2_2_6_1","volume-title":"Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement. national conference on artificial intelligence","author":"Deng Jianing","year":"2020","unstructured":"Jianing Deng , Li Wang , Shiliang Pu , and Cheng Zhuo . 2020. Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement. national conference on artificial intelligence ( 2020 ). Jianing Deng, Li Wang, Shiliang Pu, and Cheng Zhuo. 2020. Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement. national conference on artificial intelligence (2020)."},{"key":"e_1_3_2_2_7_1","volume-title":"et al","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 , et al . 2020 . An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020). 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. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_30"},{"key":"e_1_3_2_2_10_1","volume-title":"Cross-Modality High-Frequency Transformer for MR Image Super-Resolution. arXiv preprint arXiv:2203.15314","author":"Fang Chaowei","year":"2022","unstructured":"Chaowei Fang , Dingwen Zhang , Liang Wang , Yulun Zhang , Lechao Cheng , and Junwei Han . 2022. Cross-Modality High-Frequency Transformer for MR Image Super-Resolution. arXiv preprint arXiv:2203.15314 ( 2022 ). Chaowei Fang, Dingwen Zhang, Liang Wang, Yulun Zhang, Lechao Cheng, and Junwei Han. 2022. Cross-Modality High-Frequency Transformer for MR Image Super-Resolution. arXiv preprint arXiv:2203.15314 (2022)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_2_13_1","volume-title":"International Conference on Machine Learning. PMLR, 1243--1252","author":"Gehring Jonas","year":"2017","unstructured":"Jonas Gehring , Michael Auli , David Grangier , Denis Yarats , and Yann N Dauphin . 2017 . Convolutional sequence to sequence learning . In International Conference on Machine Learning. PMLR, 1243--1252 . Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, and Yann N Dauphin. 2017. Convolutional sequence to sequence learning. In International Conference on Machine Learning. PMLR, 1243--1252."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113165"},{"key":"e_1_3_2_2_16_1","volume-title":"Attention in Attention: Modeling Context Correlation for Efficient Video Classification","author":"Hao Yanbin","year":"2022","unstructured":"Yanbin Hao , Shuo Wang , Pei Cao , Xinjian Gao , Tong Xu , Jinmeng Wu , and Xiangnan He. 2022. Attention in Attention: Modeling Context Correlation for Efficient Video Classification . IEEE Transactions on Circuits and Systems for Video Technology ( 2022 ). Yanbin Hao, Shuo Wang, Pei Cao, Xinjian Gao, Tong Xu, Jinmeng Wu, and Xiangnan He. 2022. Attention in Attention: Modeling Context Correlation for Efficient Video Classification. IEEE Transactions on Circuits and Systems for Video Technology (2022)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00100"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413595"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_20_1","volume-title":"Determining optical flow. Artificial intelligence 17, 1--3","author":"Horn Berthold KP","year":"1981","unstructured":"Berthold KP Horn and Brian G Schunck . 1981. Determining optical flow. Artificial intelligence 17, 1--3 ( 1981 ), 185--203. Berthold KP Horn and Brian G Schunck. 1981. Determining optical flow. Artificial intelligence 17, 1--3 (1981), 185--203."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"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":"Relational Self-Attention: What's Missing in Attention for Video Understanding. Advances in Neural Information Processing Systems 34","author":"Kim Manjin","year":"2021","unstructured":"Manjin Kim , Heeseung Kwon , Chunyu Wang , Suha Kwak , and Minsu Cho . 2021. Relational Self-Attention: What's Missing in Attention for Video Understanding. Advances in Neural Information Processing Systems 34 ( 2021 ). Manjin Kim, Heeseung Kwon, Chunyu Wang, Suha Kwak, and Minsu Cho. 2021. Relational Self-Attention: What's Missing in Attention for Video Understanding. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_2_24_1","volume-title":"MoViNets: Mobile Video Networks for Efficient Video Recognition. computer vision and pattern recognition","author":"Kondratyuk Dan","year":"2021","unstructured":"Dan Kondratyuk , Liangzhe Yuan , Yandong Li , Li Zhang , Mingxing Tan , Matthew Brown , and Boqing Gong . 2021. MoViNets: Mobile Video Networks for Efficient Video Recognition. computer vision and pattern recognition ( 2021 ). Dan Kondratyuk, Liangzhe Yuan, Yandong Li, Li Zhang, Mingxing Tan, Matthew Brown, and Boqing Gong. 2021. MoViNets: Mobile Video Networks for Efficient Video Recognition. computer vision and pattern recognition (2021)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01282"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"e_1_3_2_2_32_1","volume-title":"Video Swin Transformer. arXiv preprint arXiv:2106.13230","author":"Liu Ze","year":"2021","unstructured":"Ze Liu , Jia Ning , Yue Cao , Yixuan Wei , Zheng Zhang , Stephen Lin , and Han Hu. 2021. Video Swin Transformer. arXiv preprint arXiv:2106.13230 ( 2021 ). Ze Liu, Jia Ning, Yue Cao, Yixuan Wei, Zheng Zhang, Stephen Lin, and Han Hu. 2021. Video Swin Transformer. arXiv preprint arXiv:2106.13230 (2021)."},{"key":"e_1_3_2_2_33_1","volume-title":"TAM: Temporal Adaptive Module for Video Recognition. arXiv preprint arXiv:2005.06803","author":"Liu Zhaoyang","year":"2020","unstructured":"Zhaoyang Liu , Limin Wang , Wayne Wu , Chen Qian , and Tong Lu . 2020 . TAM: Temporal Adaptive Module for Video Recognition. arXiv preprint arXiv:2005.06803 (2020). Zhaoyang Liu, Limin Wang, Wayne Wu, Chen Qian, and Tong Lu. 2020. TAM: Temporal Adaptive Module for Video Recognition. arXiv preprint arXiv:2005.06803 (2020)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"e_1_3_2_2_35_1","volume-title":"On the effectiveness of task granularity for transfer learning. arXiv preprint arXiv:1804.09235","author":"Mahdisoltani Farzaneh","year":"2018","unstructured":"Farzaneh Mahdisoltani , Guillaume Berger , Waseem Gharbieh , David Fleet , and Roland Memisevic . 2018. On the effectiveness of task granularity for transfer learning. arXiv preprint arXiv:1804.09235 ( 2018 ). Farzaneh Mahdisoltani, Guillaume Berger, Waseem Gharbieh, David Fleet, and Roland Memisevic. 2018. On the effectiveness of task granularity for transfer learning. arXiv preprint arXiv:1804.09235 (2018)."},{"key":"e_1_3_2_2_36_1","volume-title":"Keeping your eye on the ball: Trajectory attention in video transformers. Advances in Neural Information Processing Systems 34","author":"Patrick Mandela","year":"2021","unstructured":"Mandela Patrick , Dylan Campbell , Yuki Asano , Ishan Misra , Florian Metze , Christoph Feichtenhofer , Andrea Vedaldi , and Jo\u00e3o F Henriques . 2021. Keeping your eye on the ball: Trajectory attention in video transformers. Advances in Neural Information Processing Systems 34 ( 2021 ). Mandela Patrick, Dylan Campbell, Yuki Asano, Ishan Misra, Florian Metze, Christoph Feichtenhofer, Andrea Vedaldi, and Jo\u00e3o F Henriques. 2021. Keeping your eye on the ball: Trajectory attention in video transformers. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"e_1_3_2_2_38_1","volume-title":"International Journal of Computer Vision","author":"Selvaraju Ramprasaath R.","year":"2016","unstructured":"Ramprasaath R. Selvaraju , Michael Cogswell , Abhishek Das , Ramakrishna Vedantam , Devi Parikh , and Dhruv Batra . 2016. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization . International Journal of Computer Vision ( 2016 ). Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. 2016. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. International Journal of Computer Vision (2016)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"e_1_3_2_2_40_1","volume-title":"Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"e_1_3_2_2_42_1","volume-title":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition. arXiv preprint arXiv:1807.11794","author":"Sudhakaran Swathikiran","year":"2018","unstructured":"Swathikiran Sudhakaran and Oswald Lanz . 2018. Attention is all we need: Nailing down object-centric attention for egocentric activity recognition. arXiv preprint arXiv:1807.11794 ( 2018 ). Swathikiran Sudhakaran and Oswald Lanz. 2018. Attention is all we need: Nailing down object-centric attention for egocentric activity recognition. arXiv preprint arXiv:1807.11794 (2018)."},{"key":"e_1_3_2_2_43_1","volume-title":"Vimpac: Video pre-training via masked token prediction and contrastive learning. arXiv preprint arXiv:2106.11250","author":"Tan Hao","year":"2021","unstructured":"Hao Tan , Jie Lei , Thomas Wolf , and Mohit Bansal . 2021 . Vimpac: Video pre-training via masked token prediction and contrastive learning. arXiv preprint arXiv:2106.11250 (2021). Hao Tan, Jie Lei, Thomas Wolf, and Mohit Bansal. 2021. Vimpac: Video pre-training via masked token prediction and contrastive learning. arXiv preprint arXiv:2106.11250 (2021)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475218"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_2_48_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 NIPS.  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 NIPS."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6907"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"e_1_3_2_2_55_1","volume-title":"Token Shift Transformer for Video Classification. acm multimedia","author":"Zhang Hao","year":"2021","unstructured":"Hao Zhang , Yanbin Hao , and Chong-Wah Ngo . 2021. Token Shift Transformer for Video Classification. acm multimedia ( 2021 ). Hao Zhang, Yanbin Hao, and Chong-Wah Ngo. 2021. Token Shift Transformer for Video Classification. acm multimedia (2021)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475272"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2884478"},{"key":"e_1_3_2_2_58_1","volume-title":"International Conference on Learning Representations.","author":"Zhang Shiwen","year":"2019","unstructured":"Shiwen Zhang , Sheng Guo , Weilin Huang , Matthew R Scott , and Limin Wang . 2019 . V4D: 4D Convolutional Neural Networks for Video-level Representation Learning . In International Conference on Learning Representations. Shiwen Zhang, Sheng Guo, Weilin Huang, Matthew R Scott, and Limin Wang. 2019. V4D: 4D Convolutional Neural Networks for Video-level Representation Learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"e_1_3_2_2_60_1","volume-title":"Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, Trevor Back, Paul Natsev, and Mustafa Suleyman.","author":"Zisserman Andrew","year":"2017","unstructured":"Andrew Zisserman , Joao Carreira , Karen Simonyan , Will Kay , Brian Hu Zhang , Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, Trevor Back, Paul Natsev, and Mustafa Suleyman. 2017 . The Kinetics Human Action Video Dataset. arXiv: Computer Vision and Pattern Recognition ( 2017). Andrew Zisserman, Joao Carreira, Karen Simonyan, Will Kay, Brian Hu Zhang, Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, Trevor Back, Paul Natsev, and Mustafa Suleyman. 2017. The Kinetics Human Action Video Dataset. arXiv: Computer Vision and Pattern Recognition (2017)."}],"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\/3503161.3547841","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3547841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:35Z","timestamp":1750186955000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547841"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":60,"alternative-id":["10.1145\/3503161.3547841","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3547841","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"}}]}}