{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:23:39Z","timestamp":1750220619150,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413709","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:26:18Z","timestamp":1602505578000},"page":"3947-3955","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Deep Multi-modality Soft-decoding of Very Low Bit-rate Face Videos"],"prefix":"10.1145","author":[{"given":"Yanhui","family":"Guo","sequence":"first","affiliation":[{"name":"McMaster University, Hamilton, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Wu","sequence":"additional","affiliation":[{"name":"McMaster University, Hamilton, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the 30th International Conference on Machine Learning (Proceedings of Machine Learning Research), Sanjoy Dasgupta and David McAllester (Eds.)","volume":"28","author":"Andrew Galen","year":"2013","unstructured":"Galen Andrew , Raman Arora , Jeff Bilmes , and Karen Livescu . 2013 . Deep Canonical Correlation Analysis . In Proceedings of the 30th International Conference on Machine Learning (Proceedings of Machine Learning Research), Sanjoy Dasgupta and David McAllester (Eds.) , Vol. 28 . PMLR, Atlanta, Georgia, USA, 1247--1255. http:\/\/proceedings.mlr.press\/v28\/andrew13.html Galen Andrew, Raman Arora, Jeff Bilmes, and Karen Livescu. 2013. Deep Canonical Correlation Analysis. In Proceedings of the 30th International Conference on Machine Learning (Proceedings of Machine Learning Research), Sanjoy Dasgupta and David McAllester (Eds.), Vol. 28. PMLR, Atlanta, Georgia, USA, 1247--1255. http:\/\/proceedings.mlr.press\/v28\/andrew13.html"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_2_1","DOI":"10.1109\/FG.2018.00019"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_3_1","DOI":"10.1109\/ICCV.2017.89"},{"volume-title":"Deep Back-Projection Networks for Super-Resolution. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1664--1673","author":"Haris M.","unstructured":"M. Haris , G. Shakhnarovich , and N. Ukita . 2018 . Deep Back-Projection Networks for Super-Resolution. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1664--1673 . M. Haris, G. Shakhnarovich, and N. Ukita. 2018. Deep Back-Projection Networks for Super-Resolution. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1664--1673.","key":"e_1_3_2_2_4_1"},{"doi-asserted-by":"crossref","unstructured":"Xiaoyi He Qiang Hu Xiaoyun Zhang Zhang Chongyang Weiyao Lin and Xintong Han. 2018. Enhancing HEVC Compressed Videos with a Partition-Masked Convolutional Neural Network. 216--220. https:\/\/doi.org\/10.1109\/ICIP.2018.8451086 10.1109\/ICIP.2018.8451086","key":"#cr-split#-e_1_3_2_2_5_1.1","DOI":"10.1109\/ICIP.2018.8451086"},{"doi-asserted-by":"crossref","unstructured":"Xiaoyi He Qiang Hu Xiaoyun Zhang Zhang Chongyang Weiyao Lin and Xintong Han. 2018. Enhancing HEVC Compressed Videos with a Partition-Masked Convolutional Neural Network. 216--220. https:\/\/doi.org\/10.1109\/ICIP.2018.8451086","key":"#cr-split#-e_1_3_2_2_5_1.2","DOI":"10.1109\/ICIP.2018.8451086"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_6_1","DOI":"10.1109\/TIP.2019.2916751"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_7_1","DOI":"10.1007\/s11263-019-01150-y"},{"key":"e_1_3_2_2_8_1","volume-title":"Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Jo Younghyun","year":"2018","unstructured":"Younghyun Jo , Seoung Wug Oh , Jaeyeon Kang , and Seon Joo Kim . 2018 . Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Younghyun Jo, Seoung Wug Oh, Jaeyeon Kang, and Seon Joo Kim. 2018. Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_9_1","volume-title":"MMTM: Multimodal Transfer Module for CNN Fusion. arXiv preprint arXiv:1911.08670","author":"Vaezi Joze Hamid Reza","year":"2019","unstructured":"Hamid Reza Vaezi Joze , Amirreza Shaban , Michael L Iuzzolino , and Kazuhito Koishida . 2019 . MMTM: Multimodal Transfer Module for CNN Fusion. arXiv preprint arXiv:1911.08670 (2019). Hamid Reza Vaezi Joze, Amirreza Shaban, Michael L Iuzzolino, and Kazuhito Koishida. 2019. MMTM: Multimodal Transfer Module for CNN Fusion. arXiv preprint arXiv:1911.08670 (2019)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_10_1","DOI":"10.1145\/2818346.2830590"},{"key":"e_1_3_2_2_11_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980."},{"volume-title":"2015 IEEE International Conference on Computer Vision (ICCV). 531--539","author":"Liao R.","unstructured":"R. Liao , X. Tao , R. Li , Z. Ma , and J. Jia . 2015a. Video Super-Resolution via Deep Draft-Ensemble Learning . In 2015 IEEE International Conference on Computer Vision (ICCV). 531--539 . R. Liao, X. Tao, R. Li, Z. Ma, and J. Jia. 2015a. Video Super-Resolution via Deep Draft-Ensemble Learning. In 2015 IEEE International Conference on Computer Vision (ICCV). 531--539.","key":"e_1_3_2_2_12_1"},{"volume-title":"2015 IEEE International Conference on Computer Vision (ICCV). 531--539","author":"Liao R.","unstructured":"R. Liao , X. Tao , R. Li , Z. Ma , and J. Jia . 2015b. Video Super-Resolution via Deep Draft-Ensemble Learning . In 2015 IEEE International Conference on Computer Vision (ICCV). 531--539 . R. Liao, X. Tao, R. Li, Z. Ma, and J. Jia. 2015b. Video Super-Resolution via Deep Draft-Ensemble Learning. In 2015 IEEE International Conference on Computer Vision (ICCV). 531--539.","key":"e_1_3_2_2_13_1"},{"key":"e_1_3_2_2_14_1","volume-title":"Russo","author":"Livingstone Steven R.","year":"2018","unstructured":"Steven R. Livingstone and Frank A . Russo . 2018 . The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English. PLOS ONE , Vol. 13 , 5 (05 2018), 1--35. https:\/\/doi.org\/10.1371\/journal.pone.0196391 10.1371\/journal.pone.0196391 Steven R. Livingstone and Frank A. Russo. 2018. The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English. PLOS ONE, Vol. 13, 5 (05 2018), 1--35. https:\/\/doi.org\/10.1371\/journal.pone.0196391"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_15_1","DOI":"10.1007\/978-3-030-01264-9_35"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_16_1","DOI":"10.1007\/978-3-030-01258-8_18"},{"unstructured":"Jiquan Ngiam Aditya Khosla Mingyu Kim Juhan Nam Honglak Lee and Andrew Y Ng. 2011. Multimodal deep learning. (2011).  Jiquan Ngiam Aditya Khosla Mingyu Kim Juhan Nam Honglak Lee and Andrew Y Ng. 2011. Multimodal deep learning. (2011).","key":"e_1_3_2_2_17_1"},{"unstructured":"WV Friesen P Ekman and J Hager. 1978. Facial Action Coding System: A Technique for the Measurement of Facial Movement.  WV Friesen P Ekman and J Hager. 1978. Facial Action Coding System: A Technique for the Measurement of Facial Movement.","key":"e_1_3_2_2_18_1"},{"key":"e_1_3_2_2_19_1","volume-title":"Bogdan Raducanu, and Jose M \u00c1lvarez.","author":"Perarnau Guim","year":"2016","unstructured":"Guim Perarnau , Joost Van De Weijer , Bogdan Raducanu, and Jose M \u00c1lvarez. 2016 . Invertible conditional gans for image editing. arXiv preprint arXiv:1611.06355 (2016). Guim Perarnau, Joost Van De Weijer, Bogdan Raducanu, and Jose M \u00c1lvarez. 2016. Invertible conditional gans for image editing. arXiv preprint arXiv:1611.06355 (2016)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_20_1","DOI":"10.1109\/CVPR.2019.00713"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_21_1","DOI":"10.1016\/j.specom.2011.11.004"},{"key":"e_1_3_2_2_22_1","volume-title":"A novel windowing technique for efficient computation of MFCC for speaker recognition","author":"Sahidullah Md","year":"2012","unstructured":"Md Sahidullah and Goutam Saha . 2012b. A novel windowing technique for efficient computation of MFCC for speaker recognition . IEEE signal processing letters, Vol. 20 , 2 ( 2012 ), 149--152. Md Sahidullah and Goutam Saha. 2012b. A novel windowing technique for efficient computation of MFCC for speaker recognition. IEEE signal processing letters, Vol. 20, 2 (2012), 149--152."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_23_1","DOI":"10.1109\/76.554415"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_24_1","DOI":"10.1109\/TCSVT.2012.2221191"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_25_1","DOI":"10.1145\/3072959.3073640"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_26_1","DOI":"10.1109\/ICCV.2017.479"},{"key":"e_1_3_2_2_27_1","volume-title":"TDAN: Temporally Deformable Alignment Network for Video Super-Resolution.","author":"Tian Yapeng","year":"2018","unstructured":"Yapeng Tian , Yulun Zhang , Yun Fu , and Chenliang Xu . 2018 . TDAN: Temporally Deformable Alignment Network for Video Super-Resolution. Yapeng Tian, Yulun Zhang, Yun Fu, and Chenliang Xu. 2018. TDAN: Temporally Deformable Alignment Network for Video Super-Resolution."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_28_1","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_2_29_1","volume-title":"EDVR: Video Restoration with Enhanced Deformable Convolutional Networks. CoRR","author":"Wang Xintao","year":"2019","unstructured":"Xintao Wang , Kelvin C. K. Chan , Ke Yu , Chao Dong , and Chen Change Loy . 2019 . EDVR: Video Restoration with Enhanced Deformable Convolutional Networks. CoRR , Vol. abs\/ 1905 .02716. arxiv: 1905.02716 http:\/\/arxiv.org\/abs\/1905.02716 Xintao Wang, Kelvin C. K. Chan, Ke Yu, Chao Dong, and Chen Change Loy. 2019. EDVR: Video Restoration with Enhanced Deformable Convolutional Networks. CoRR, Vol. abs\/1905.02716. arxiv: 1905.02716 http:\/\/arxiv.org\/abs\/1905.02716"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_30_1","DOI":"10.1109\/CVPR.2018.00813"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_31_1","DOI":"10.1109\/TCSVT.2003.815165"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_32_1","DOI":"10.1007\/978-3-030-01261-8_41"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_33_1","DOI":"10.1109\/ICCV.2019.00714"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_34_1","DOI":"10.1007\/s11263-018-01144-2"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_35_1","DOI":"10.1109\/CVPR.2018.00697"},{"key":"e_1_3_2_2_36_1","volume-title":"Multi-Frame Quality Enhancement for Compressed Video. (03","author":"Yang Ren","year":"2018","unstructured":"Ren Yang , Mai Xu , Zulin Wang , and Tianyi Li. 2018b. Multi-Frame Quality Enhancement for Compressed Video. (03 2018 ). Ren Yang, Mai Xu, Zulin Wang, and Tianyi Li. 2018b. Multi-Frame Quality Enhancement for Compressed Video. (03 2018)."},{"doi-asserted-by":"crossref","unstructured":"Shiqing Zhang Shiliang Zhang Tiejun Huang and Wen Gao. 2016. Multimodal Deep Convolutional Neural Network for Audio-Visual Emotion Recognition. 281--284. https:\/\/doi.org\/10.1145\/2911996.2912051 10.1145\/2911996.2912051","key":"#cr-split#-e_1_3_2_2_37_1.1","DOI":"10.1145\/2911996.2912051"},{"doi-asserted-by":"crossref","unstructured":"Shiqing Zhang Shiliang Zhang Tiejun Huang and Wen Gao. 2016. Multimodal Deep Convolutional Neural Network for Audio-Visual Emotion Recognition. 281--284. https:\/\/doi.org\/10.1145\/2911996.2912051","key":"#cr-split#-e_1_3_2_2_37_1.2","DOI":"10.1145\/2911996.2912051"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '20","name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA"},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413709","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:16Z","timestamp":1750197676000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":39,"alternative-id":["10.1145\/3394171.3413709","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413709","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}