{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:59:57Z","timestamp":1772553597998,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"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":["2017YFB1002202"],"award-info":[{"award-number":["2017YFB1002202"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350997","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"130-138","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Multimodal Deep Denoise Framework for Affective Video Content Analysis"],"prefix":"10.1145","author":[{"given":"Yaochen","family":"Zhu","sequence":"first","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenzhong","family":"Chen","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079027"},{"key":"e_1_3_2_1_2_1","first-page":"1","article-title":"Multimodal Machine Learning: A Survey and Taxonomy","volume":"99","author":"Baltruaitis Tadas","year":"2017","journal-title":"PP"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2396531"},{"key":"e_1_3_2_1_4_1","first-page":"0","article-title":"Variational Inference: A Review for Statisticians","volume":"112","author":"Blei David M.","year":"2018","journal-title":"J. Amer. Statist. Assoc."},{"key":"e_1_3_2_1_5_1","volume-title":"Meghna Pandharipande, Ehtesham Hassan, Hiranmay Ghosh, and Sunil Kumar Kopparapu.","author":"Chakraborty Rupayan","year":"2015"},{"key":"e_1_3_2_1_6_1","unstructured":"Qi Dai Rui-Wei Zhao Zuxuan Wu Xi Wang Zichen Gu Wenhai Wu and Yu-Gang Jiang. 2015. Fudan-Huawei at MediaEval 2015: Detecting Violent Scenes and Affective Impact in Movies with Deep Learning.. In MediaEval .  Qi Dai Rui-Wei Zhao Zuxuan Wu Xi Wang Zichen Gu Wenhai Wu and Yu-Gang Jiang. 2015. Fudan-Huawei at MediaEval 2015: Detecting Violent Scenes and Affective Impact in Movies with Deep Learning.. In MediaEval ."},{"key":"e_1_3_2_1_7_1","volume-title":"ImageNet: A large-scale hierarchical image database","author":"Deng Jia","year":"2009"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"e_1_3_2_1_9_1","volume-title":"Classification in the presence of label noise: a survey","author":"Michel Verleysen Fr\u00e9nay","year":"2014"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2006.1621452"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.840618"},{"key":"e_1_3_2_1_13_1","volume-title":"Deep Residual Learning for Image Recognition. CoRR","author":"He Kaiming","year":"2015"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Shawn Hershey Sourish Chaudhuri Daniel P. W. Ellis Jort F. Gemmeke Aren Jansen R. Channing Moore Manoj Plakal Devin Platt Rif A. Saurous and Bryan Seybold. 2016. CNN architectures for large-scale audio classification. (2016).  Shawn Hershey Sourish Chaudhuri Daniel P. W. Ellis Jort F. Gemmeke Aren Jansen R. Channing Moore Manoj Plakal Devin Platt Rif A. Saurous and Bryan Seybold. 2016. CNN architectures for large-scale audio classification. (2016).","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Geoffrey E. Hinton. 2002. Training Products of Experts by Minimizing Contrastive . p\u00e1gs. 1771--1800 pages.  Geoffrey E. Hinton. 2002. Training Products of Experts by Minimizing Contrastive . p\u00e1gs. 1771--1800 pages.","DOI":"10.1162\/089976602760128018"},{"key":"e_1_3_2_1_16_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997"},{"key":"e_1_3_2_1_17_1","first-page":"1611","volume-title":"Article arXiv:1611.01144 (Nov","author":"Jang Eric","year":"2016"},{"key":"e_1_3_2_1_18_1","volume-title":"IEEE International Conference on Data Mining .","author":"Jindal Ishan","year":"2017"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957066"},{"key":"e_1_3_2_1_20_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015"},{"key":"e_1_3_2_1_21_1","first-page":"1312","volume-title":"Article arXiv:1312.6114 (Dec","author":"Kingma Diederik P","year":"2013"},{"key":"e_1_3_2_1_22_1","unstructured":"Vu Lam Duy-Dinh Le and Duc Anh Duong. 2015. NII-UIT at MediaEval 2015 Affective Impact of Movies Task.. In MediaEval .  Vu Lam Duy-Dinh Le and Duc Anh Duong. 2015. NII-UIT at MediaEval 2015 Affective Impact of Movies Task.. In MediaEval ."},{"key":"e_1_3_2_1_23_1","first-page":"1","article-title":"Deep Multimodal Learning for Affective Analysis and Retrieval","volume":"17","author":"Lei Pang","year":"2015","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_2_1_24_1","first-page":"1611","volume-title":"Article arXiv:1611.00712 (Nov","author":"Maddison Chris J.","year":"2016"},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Multimedia .","author":"Min Xu","year":"2008"},{"key":"e_1_3_2_1_26_1","unstructured":"Ionut Mironica Bogdan Ionescu Mats Sj\u00f6berg Markus Schedl and Marcin Skowron. 2015. RFA at MediaEval 2015 Affective Impact of Movies Task: A Multimodal Approach.. In MediaEval .  Ionut Mironica Bogdan Ionescu Mats Sj\u00f6berg Markus Schedl and Marcin Skowron. 2015. RFA at MediaEval 2015 Affective Impact of Movies Task: A Multimodal Approach.. In MediaEval ."},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Machine Learning .","author":"Mnih Volodymyr","year":"2013"},{"key":"e_1_3_2_1_28_1","volume-title":"Riedmiller","author":"Mnih Volodymyr","year":"2013"},{"key":"e_1_3_2_1_29_1","volume-title":"A study of the effect of different types of noise on the precision of supervised learning techniques. Artificial intelligence review","author":"Nettleton David F","year":"2010"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"e_1_3_2_1_31_1","volume-title":"IEEE International Conference on Computer Vision .","author":"Quan Gan","year":"2017"},{"key":"e_1_3_2_1_32_1","unstructured":"Omar Seddati Emre Kulah Gueorgui Pironkov St\u00e9phane Dupont Sa\"id Mahmoudi and Thierry Dutoit. 2015. UMons at MediaEval 2015 Affective Impact of Movies Task including Violent Scenes Detection.. In MediaEval .  Omar Seddati Emre Kulah Gueorgui Pironkov St\u00e9phane Dupont Sa\"id Mahmoudi and Thierry Dutoit. 2015. UMons at MediaEval 2015 Affective Impact of Movies Task including Violent Scenes Detection.. In MediaEval ."},{"key":"e_1_3_2_1_33_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Workshop Track Proceedings . http:\/\/arxiv.org\/abs\/1406","author":"Sukhbaatar Sainbayar","year":"2015"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/1698924.1699063"},{"key":"e_1_3_2_1_35_1","volume-title":"Rethinking the Inception Architecture for Computer Vision. CoRR","author":"Szegedy Christian","year":"2015"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Xiao Tong Xia Tian Yang Yi Huang Chang and Xiaogang Wang. 2015. Learning from massive noisy labeled data for image classification. In Computer Vision & Pattern Recognition .  Xiao Tong Xia Tian Yang Yi Huang Chang and Xiaogang Wang. 2015. Learning from massive noisy labeled data for image classification. In Computer Vision & Pattern Recognition .","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"e_1_3_2_1_38_1","unstructured":"George Trigeorgis Eduardo Coutinho Fabien Ringeval Erik Marchi Stefanos Zafeiriou and Bj\u00f6rn W Schuller. 2015. The ICL-TUM-PASSAU Approach for the MediaEval 2015\" Affective Impact of Movies\" Task.. In MediaEval .  George Trigeorgis Eduardo Coutinho Fabien Ringeval Erik Marchi Stefanos Zafeiriou and Bj\u00f6rn W Schuller. 2015. The ICL-TUM-PASSAU Approach for the MediaEval 2015\" Affective Impact of Movies\" Task.. In MediaEval ."},{"key":"e_1_3_2_1_39_1","unstructured":"Marin Vlastelica Sergey Hayrapetyan Makarand Tapaswi and Rainer Stiefelhagen. 2015. Kit at mediaeval 2015-evaluating visual cues for affective impact of movies task. (2015).  Marin Vlastelica Sergey Hayrapetyan Makarand Tapaswi and Rainer Stiefelhagen. 2015. Kit at mediaeval 2015-evaluating visual cues for affective impact of movies task. (2015)."},{"key":"e_1_3_2_1_40_1","volume-title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition. CoRR","author":"Wang Limin","year":"2016"},{"key":"e_1_3_2_1_41_1","volume-title":"Multimodal Generative Models for Scalable Weakly-Supervised Learning. CoRR","author":"Wu Mike","year":"2018"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2877939"},{"key":"e_1_3_2_1_43_1","volume-title":"Multi-modal learning for affective content analysis in movies. Multimedia Tools and Applications","author":"Yi Yun","year":"2018"},{"key":"e_1_3_2_1_44_1","volume-title":"Visualizing and Understanding Convolutional Networks. In European Conference on Computer Vision .","author":"Matthew"},{"key":"e_1_3_2_1_45_1","volume-title":"Platt","author":"Zhou Dengyong","year":"2012"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","location":"Nice France","acronym":"MM '19","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350997","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:18Z","timestamp":1750201998000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350997"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":45,"alternative-id":["10.1145\/3343031.3350997","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350997","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}