{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T20:03:05Z","timestamp":1785700985730,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":65,"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"}],"funder":[{"name":"Singapore National Cybersecurity R&D Program","award":["NRF2018NCR-NCR005-0001"],"award-info":[{"award-number":["NRF2018NCR-NCR005-0001"]}]},{"name":"National Satellite of Excellence in Trustworthy Software System","award":["NRF2018NCR-NSOE003-0001"],"award-info":[{"award-number":["NRF2018NCR-NSOE003-0001"]}]},{"name":"NRF Investigatorship","award":["NRFI06-2020-0022"],"award-info":[{"award-number":["NRFI06-2020-0022"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413716","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:26:18Z","timestamp":1602505578000},"page":"1207-1216","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":106,"title":["DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices"],"prefix":"10.1145","author":[{"given":"Run","family":"Wang","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Juefei-Xu","sequence":"additional","affiliation":[{"name":"Alibaba Group, San Mateo, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihao","family":"Huang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Guo","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofei","family":"Xie","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Ma","sequence":"additional","affiliation":[{"name":"Kyushu University, Fukuoka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technology University & Zhejiang University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 104--109","author":"AlBadawy Ehab A","year":"2019"},{"key":"e_1_3_2_2_2_1","unstructured":"Christopher M Bishop. 1994. Mixture density networks. (1994).  Christopher M Bishop. 1994. Mixture density networks. (1994)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"P. Buchana I. Cazan M. Diaz-Granados F. Juefei-Xu and M.Savvides. 2016. Simultaneous Forgery Identification and Localization in Paintings Using Advanced Correlation Filters. In ICIP.  P. Buchana I. Cazan M. Diaz-Granados F. Juefei-Xu and M.Savvides. 2016. Simultaneous Forgery Identification and Localization in Paintings Using Advanced Correlation Filters. In ICIP.","DOI":"10.1109\/ICIP.2016.7532336"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Shan Carter Zan Armstrong Ludwig Schubert Ian Johnson and Chris Olah. 2019. Activation Atlas. Distill (2019). https:\/\/doi.org\/10.23915\/distill.00015 https:\/\/distill.pub\/2019\/activation-atlas.  Shan Carter Zan Armstrong Ludwig Schubert Ian Johnson and Chris Olah. 2019. Activation Atlas. Distill (2019). https:\/\/doi.org\/10.23915\/distill.00015 https:\/\/distill.pub\/2019\/activation-atlas.","DOI":"10.23915\/distill.00015"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"e_1_3_2_2_6_1","unstructured":"Alexander Comerford. 2019. Detecting audio deep fakes with bispectral analysis. https:\/\/github.com\/cmrfrd\/DetectingDeepFakes_BlackHat2019. (2019).  Alexander Comerford. 2019. Detecting audio deep fakes with bispectral analysis. https:\/\/github.com\/cmrfrd\/DetectingDeepFakes_BlackHat2019. (2019)."},{"key":"e_1_3_2_2_7_1","unstructured":"Amazon Corporation. 2020 a. Amazon AWS Polly. https:\/\/aws.amazon.com\/polly. (2020).  Amazon Corporation. 2020 a. Amazon AWS Polly. https:\/\/aws.amazon.com\/polly. (2020)."},{"key":"e_1_3_2_2_8_1","unstructured":"Baidu Corporation. 2020 b. Baidu Text-to-Speech System. https:\/\/cloud.baidu.com\/product\/speech\/tts. (2020).  Baidu Corporation. 2020 b. Baidu Text-to-Speech System. https:\/\/cloud.baidu.com\/product\/speech\/tts. (2020)."},{"key":"e_1_3_2_2_9_1","unstructured":"Google Corporation. 2020 c. Google Cloud TTS. https:\/\/cloud.google.com\/text-to-speech. (2020).  Google Corporation. 2020 c. Google Cloud TTS. https:\/\/cloud.google.com\/text-to-speech. (2020)."},{"key":"e_1_3_2_2_10_1","unstructured":"DeepMind. 2020. WaveNet: A generative model for raw audio. https:\/\/deepmind.com\/blog\/article\/wavenet-generative-model-raw-audio. (2020).  DeepMind. 2020. WaveNet: A generative model for raw audio. https:\/\/deepmind.com\/blog\/article\/wavenet-generative-model-raw-audio. (2020)."},{"key":"e_1_3_2_2_11_1","unstructured":"Ian J Goodfellow Jonathon Shlens and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014).  Ian J Goodfellow Jonathon Shlens and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1506"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413732"},{"key":"e_1_3_2_2_14_1","unstructured":"Yihao Huang Felix Juefei-Xu Run Wang Qing Guo Xiaofei Xie Lei Ma Jianwen Li Weikai Miao Yang Liu and Geguang Pu. 2020 b. FakeLocator: Robust Localization of GAN-Based Face Manipulations. arXiv preprint arXiv:2001.09598 (2020).  Yihao Huang Felix Juefei-Xu Run Wang Qing Guo Xiaofei Xie Lei Ma Jianwen Li Weikai Miao Yang Liu and Geguang Pu. 2020 b. FakeLocator: Robust Localization of GAN-Based Face Manipulations. arXiv preprint arXiv:2001.09598 (2020)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Liming Jiang Ren Li Wayne Wu Chen Qian and Chen Change Loy. 2020. DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection. In CVPR.  Liming Jiang Ren Li Wayne Wu Chen Qian and Chen Change Loy. 2020. DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.17226\/25488"},{"key":"e_1_3_2_2_17_1","unstructured":"The Wall Street Journal. 2019. Fraudsters Used AI to Mimic CEO's Voice in Unusual Cybercrime Case. https:\/\/www.wsj.com\/articles\/fraudsters-use-ai-to-mimic-ceos-voice-in-unusual-cybercrime-case-11567157402. (2019).  The Wall Street Journal. 2019. Fraudsters Used AI to Mimic CEO's Voice in Unusual Cybercrime Case. https:\/\/www.wsj.com\/articles\/fraudsters-use-ai-to-mimic-ceos-voice-in-unusual-cybercrime-case-11567157402. (2019)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639225"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Tero Karras Samuli Laine Miika Aittala Janne Hellsten Jaakko Lehtinen and Timo Aila. 2019. Analyzing and improving the image quality of stylegan. arXiv preprint arXiv:1912.04958 (2019).  Tero Karras Samuli Laine Miika Aittala Janne Hellsten Jaakko Lehtinen and Timo Aila. 2019. Analyzing and improving the image quality of stylegan. arXiv preprint arXiv:1912.04958 (2019).","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Kazuhiro Kobayashi and Tomoki Toda. 2018. sprocket: Open-Source Voice Conversion Software.. Odyssey. 203--210.  Kazuhiro Kobayashi and Tomoki Toda. 2018. sprocket: Open-Source Voice Conversion Software.. Odyssey. 203--210.","DOI":"10.21437\/Odyssey.2018-29"},{"key":"e_1_3_2_2_21_1","first-page":"255","article-title":"Forensic authenticity analyses of the header data in re-encoded WMA files from small Olympus audio recorders","volume":"60","author":"Koenig Bruce E","year":"2012","journal-title":"Journal of the Audio Engineering Society"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953210"},{"key":"e_1_3_2_2_23_1","unstructured":"Yuezun Li and Siwei Lyu. 2018. Exposing deepfake videos by detecting face warping artifacts. arXiv preprint arXiv:1811.00656 (2018).  Yuezun Li and Siwei Lyu. 2018. Exposing deepfake videos by detecting face warping artifacts. arXiv preprint arXiv:1811.00656 (2018)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639187"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Jaime Lorenzo-Trueba Junichi Yamagishi Tomoki Toda Daisuke Saito Fernando Villavicencio Tomi Kinnunen and Zhenhua Ling. 2018. The voice conversion challenge 2018: Promoting development of parallel and nonparallel methods. arXiv preprint arXiv:1804.04262 (2018).  Jaime Lorenzo-Trueba Junichi Yamagishi Tomoki Toda Daisuke Saito Fernando Villavicencio Tomi Kinnunen and Zhenhua Ling. 2018. The voice conversion challenge 2018: Promoting development of parallel and nonparallel methods. arXiv preprint arXiv:1804.04262 (2018).","DOI":"10.21437\/Odyssey.2018-28"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Jorge C Lucero Jean Schoentgen and Mara Behlau. 2013. Physics-based synthesis of disordered voices.. In Interspeech. 587--591.  Jorge C Lucero Jean Schoentgen and Mara Behlau. 2013. Physics-based synthesis of disordered voices.. In Interspeech. 587--591.","DOI":"10.21437\/Interspeech.2013-161"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Lei Ma Felix Juefei-Xu Minhui Xue Bo Li Li Li Yang Liu and Jianjun Zhao. 2019. DeepCT: Tomographic Combinatorial Testing for Deep Learning Systems. In SANER.  Lei Ma Felix Juefei-Xu Minhui Xue Bo Li Li Li Yang Liu and Jianjun Zhao. 2019. DeepCT: Tomographic Combinatorial Testing for Deep Learning Systems. In SANER.","DOI":"10.1109\/SANER.2019.8668044"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238202"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"Lei Ma Fuyuan Zhang Jiyuan Sun Minhui Xue Bo Li Felix Juefei-Xu Chao Xie Li Li Yang Liu Jianjun Zhao et almbox. 2018c. DeepMutation: Mutation testing of deep learning systems. In ISSRE.  Lei Ma Fuyuan Zhang Jiyuan Sun Minhui Xue Bo Li Felix Juefei-Xu Chao Xie Li Li Yang Liu Jianjun Zhao et almbox. 2018c. DeepMutation: Mutation testing of deep learning systems. In ISSRE.","DOI":"10.1109\/ISSRE.2018.00021"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23415"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236082"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"e_1_3_2_2_33_1","unstructured":"Baidu Microsoft. 2020. Baidu TTS. https:\/\/www.home-assistant.io\/components\/tts.baidu. (2020).  Baidu Microsoft. 2020. Baidu TTS. https:\/\/www.home-assistant.io\/components\/tts.baidu. (2020)."},{"key":"e_1_3_2_2_34_1","unstructured":"Yisroel Mirsky and Wenke Lee. 2020. The Creation and Detection of Deepfakes: A Survey. arXiv preprint arXiv:2004.11138 (2020).  Yisroel Mirsky and Wenke Lee. 2020. The Creation and Detection of Deepfakes: A Survey. arXiv preprint arXiv:2004.11138 (2020)."},{"key":"e_1_3_2_2_35_1","volume-title":"TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing. In International Conference on Machine Learning. 4901--4911","author":"Odena Augustus","year":"2019"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Chris Olah Alexander Mordvintsev and Ludwig Schubert. 2017. Feature Visualization. Distill (2017). https:\/\/doi.org\/10.23915\/distill.00007 https:\/\/distill.pub\/2017\/feature-visualization.  Chris Olah Alexander Mordvintsev and Ludwig Schubert. 2017. Feature Visualization. Distill (2017). https:\/\/doi.org\/10.23915\/distill.00007 https:\/\/distill.pub\/2017\/feature-visualization.","DOI":"10.23915\/distill.00007"},{"key":"e_1_3_2_2_37_1","unstructured":"Online. 2020 a. A public lecture record Chinese dataset. http:\/\/speech.ee.ntu.edu.tw\/ yangchiyi\/lecture_tts_data.tgz. (2020).  Online. 2020 a. A public lecture record Chinese dataset. http:\/\/speech.ee.ntu.edu.tw\/ yangchiyi\/lecture_tts_data.tgz. (2020)."},{"key":"e_1_3_2_2_38_1","unstructured":"Online. 2020 b. Ancient Chinese Poetry. https:\/\/github.com\/chinese-poetry\/chinese-poetry. (2020).  Online. 2020 b. Ancient Chinese Poetry. https:\/\/github.com\/chinese-poetry\/chinese-poetry. (2020)."},{"key":"e_1_3_2_2_39_1","unstructured":"Online. 2020 c. Audio Samples: Comparison among Different Synthesis Methods. http:\/\/www.ai1000.org\/samples\/index.html. (2020).  Online. 2020 c. Audio Samples: Comparison among Different Synthesis Methods. http:\/\/www.ai1000.org\/samples\/index.html. (2020)."},{"key":"e_1_3_2_2_40_1","unstructured":"Online. 2020 d. libsora: audio and music processing in Python. https:\/\/librosa.github.io. (2020).  Online. 2020 d. libsora: audio and music processing in Python. https:\/\/librosa.github.io. (2020)."},{"key":"e_1_3_2_2_41_1","unstructured":"Online. 2020 e. Online Fake Images. https:\/\/thispersondoesnotexist.com. (2020).  Online. 2020 e. Online Fake Images. https:\/\/thispersondoesnotexist.com. (2020)."},{"key":"e_1_3_2_2_42_1","unstructured":"Online. 2020 f. Online Fake Voices. https:\/\/ttsdemo.com. (2020).  Online. 2020 f. Online Fake Voices. https:\/\/ttsdemo.com. (2020)."},{"key":"e_1_3_2_2_43_1","unstructured":"Online. 2020 g. The Audio Processing Techniques Lab at York. http:\/\/bil.eecs.yorku.ca\/aptly-lab. (2020).  Online. 2020 g. The Audio Processing Techniques Lab at York. http:\/\/bil.eecs.yorku.ca\/aptly-lab. (2020)."},{"key":"e_1_3_2_2_44_1","volume-title":"Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499","author":"van den Oord Aaron","year":"2016"},{"key":"e_1_3_2_2_45_1","unstructured":"Aaron van den Oord Nal Kalchbrenner and Koray Kavukcuoglu. 2016b. Pixel recurrent neural networks. arXiv preprint arXiv:1601.06759 (2016).  Aaron van den Oord Nal Kalchbrenner and Koray Kavukcuoglu. 2016b. Pixel recurrent neural networks. arXiv preprint arXiv:1601.06759 (2016)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132785"},{"key":"e_1_3_2_2_47_1","volume-title":"Piczak. ESC: Dataset for Environmental Sound Classification. In Proceedings of the 23rd Annual ACM Conference on Multimedia (2015--10--13)","author":"Karol"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413707"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"e_1_3_2_2_51_1","volume-title":"Attacks meet interpretability: Attribute-steered detection of adversarial samples. In Advances in Neural Information Processing Systems. 7717--7728","author":"Tao Guanhong","year":"2018"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Paul Taylor. 2009. Text-to-speech synthesis. Cambridge university press.  Paul Taylor. 2009. Text-to-speech synthesis. Cambridge university press.","DOI":"10.1017\/CBO9780511816338"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"crossref","unstructured":"Tomoki Toda Ling-Hui Chen Daisuke Saito Fernando Villavicencio Mirjam Wester Zhizheng Wu and Junichi Yamagishi. 2016. The Voice Conversion Challenge 2016.. In Interspeech. 1632--1636.  Tomoki Toda Ling-Hui Chen Daisuke Saito Fernando Villavicencio Mirjam Wester Zhizheng Wu and Junichi Yamagishi. 2016. The Voice Conversion Challenge 2016.. In Interspeech. 1632--1636.","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"crossref","unstructured":"Ruben Tolosana Ruben Vera-Rodriguez Julian Fierrez Aythami Morales and Javier Ortega-Garcia. 2020. DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection. arXiv preprint arXiv:2001.00179 (2020).  Ruben Tolosana Ruben Vera-Rodriguez Julian Fierrez Aythami Morales and Javier Ortega-Garcia. 2020. DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection. arXiv preprint arXiv:2001.00179 (2020).","DOI":"10.1016\/j.inffus.2020.06.014"},{"key":"e_1_3_2_2_56_1","unstructured":"Aaron Van den Oord Nal Kalchbrenner Lasse Espeholt Oriol Vinyals Alex Graves et almbox. 2016. Conditional image generation with pixelcnn decoders. In Advances in neural information processing systems. 4790--4798.  Aaron Van den Oord Nal Kalchbrenner Lasse Espeholt Oriol Vinyals Alex Graves et almbox. 2016. Conditional image generation with pixelcnn decoders. In Advances in neural information processing systems. 4790--4798."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/476"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"e_1_3_2_2_59_1","volume-title":"Utterance-level Aggregation For Speaker Recognition In The Wild. In International Conference on Acoustics, Speech, and Signal Processing (Oral).","author":"Xie W."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330579"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"crossref","unstructured":"Xiaoyong Yuan Pan He Qile Zhu and Xiaolin Li. 2019. Adversarial examples: Attacks and defenses for deep learning. IEEE transactions on neural networks and learning systems Vol. 30 9 (2019) 2805--2824.  Xiaoyong Yuan Pan He Qile Zhu and Xiaolin Li. 2019. Adversarial examples: Attacks and defenses for deep learning. IEEE transactions on neural networks and learning systems Vol. 30 9 (2019) 2805--2824.","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"crossref","unstructured":"Mohammed Zakariah Muhammad Khurram Khan and Hafiz Malik. 2018. Digital multimedia audio forensics: past present and future. Multimedia tools and applications Vol. 77 1 (2018) 1009--1040.  Mohammed Zakariah Muhammad Khurram Khan and Hafiz Malik. 2018. Digital multimedia audio forensics: past present and future. Multimedia tools and applications Vol. 77 1 (2018) 1009--1040.","DOI":"10.1007\/s11042-016-4277-2"},{"key":"e_1_3_2_2_64_1","unstructured":"Heiga Zen Takashi Nose Junichi Yamagishi Shinji Sako Takashi Masuko Alan W Black and Keiichi Tokuda. 2007. The HMM-based speech synthesis system (HTS) version 2.0.. In SSW. Citeseer 294--299.  Heiga Zen Takashi Nose Junichi Yamagishi Shinji Sako Takashi Masuko Alan W Black and Keiichi Tokuda. 2007. The HMM-based speech synthesis system (HTS) version 2.0.. In SSW. Citeseer 294--299."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2013.2278843"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413716","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413716","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\/3394171.3413716"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":65,"alternative-id":["10.1145\/3394171.3413716","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413716","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"}}]}}