{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T23:37:29Z","timestamp":1769557049890,"version":"3.49.0"},"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\/3394171.3413624","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T13:10:44Z","timestamp":1602508244000},"page":"3219-3227","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Crossing You in Style"],"prefix":"10.1145","author":[{"given":"Cheng-Che","family":"Lee","sequence":"first","affiliation":[{"name":"MediaTek, Hsinchu, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wan-Yi","family":"Lin","sequence":"additional","affiliation":[{"name":"National Tsing-Hua University, Hsinchu, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yen-Ting","family":"Shih","sequence":"additional","affiliation":[{"name":"National Tsing-Hua University, Hsinchu, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei-Yi (Patricia)","family":"Kuo","sequence":"additional","affiliation":[{"name":"National Tsing-Hua University, Hsinchu, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Su","sequence":"additional","affiliation":[{"name":"Academia Sinica, Taipei, Taiwan Roc"}],"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":"PERCEPTION","volume":"40","author":"Augustin M","year":"2011","unstructured":"M Augustin , Claus-Christian Carbon , and Johan Wagemans . 2011 . Measuring aesthetic impressions of visual art . PERCEPTION , Vol. 40 (01 2011), 219. M Augustin, Claus-Christian Carbon, and Johan Wagemans. 2011. Measuring aesthetic impressions of visual art. PERCEPTION, Vol. 40 (01 2011), 219."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.actpsy.2011.10.004"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1268517.1268565"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1162\/002409499552957"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Gino Brunner Yuyi Wang Roger Wattenhofer and Sumu Zhao. 2018. Symbolic music genre transfer with cyclegan. In ICTAI. 786--793.  Gino Brunner Yuyi Wang Roger Wattenhofer and Sumu Zhao. 2018. Symbolic music genre transfer with cyclegan. In ICTAI. 786--793.","DOI":"10.1109\/ICTAI.2018.00123"},{"key":"e_1_3_2_2_6_1","volume-title":"Namboodiri","author":"Chelaramani Sahil","year":"2018","unstructured":"Sahil Chelaramani , Abhishek Jha , and Anoop M . Namboodiri . 2018 . Cross-Modal Style Transfer. In ICIP. 2157--2161. Sahil Chelaramani, Abhishek Jha, and Anoop M. Namboodiri. 2018. Cross-Modal Style Transfer. In ICIP. 2157--2161."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Dongdong Chen Jing Liao Lu Yuan Nenghai Yu and Gang Hua. 2017. Coherent online video style transfer. In ICCV. 1105--1114.  Dongdong Chen Jing Liao Lu Yuan Nenghai Yu and Gang Hua. 2017. Coherent online video style transfer. In ICCV. 1105--1114.","DOI":"10.1109\/ICCV.2017.126"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1162\/002409400552829"},{"key":"e_1_3_2_2_9_1","unstructured":"Jesse Engel Cinjon Resnick Adam Roberts Sander Dieleman Mohammad Norouzi Douglas Eck and Karen Simonyan. 2017. Neural audio synthesis of musical notes with wavenet autoencoders. In ICML. 1068--1077.  Jesse Engel Cinjon Resnick Adam Roberts Sander Dieleman Mohammad Norouzi Douglas Eck and Karen Simonyan. 2017. Neural audio synthesis of musical notes with wavenet autoencoders. In ICML. 1068--1077."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Chang Gao Derun Gu Fangjun Zhang and Yizhou Yu. 2018. ReCoNet: Real-time Coherent Video Style Transfer Network. In ACCV. 637--653.  Chang Gao Derun Gu Fangjun Zhang and Yizhou Yu. 2018. ReCoNet: Real-time Coherent Video Style Transfer Network. In ACCV. 637--653.","DOI":"10.1007\/978-3-030-20876-9_40"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Leon A Gatys Alexander S Ecker and Matthias Bethge. 2016. Image style transfer using convolutional neural networks. In CVPR. 2414--2423.  Leon A Gatys Alexander S Ecker and Matthias Bethge. 2016. Image style transfer using convolutional neural networks. In CVPR. 2414--2423.","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_2_12_1","volume-title":"Transformer-NADE for Piano Performances. In NIPS 2nd Workshop on Machine Learning for Creativity and Design.","author":"Hawthorne Curtis","year":"2018","unstructured":"Curtis Hawthorne , Anna Huang , Daphne Ippolito , and Douglas Eck . 2018 . Transformer-NADE for Piano Performances. In NIPS 2nd Workshop on Machine Learning for Creativity and Design. Curtis Hawthorne, Anna Huang, Daphne Ippolito, and Douglas Eck. 2018. Transformer-NADE for Piano Performances. In NIPS 2nd Workshop on Machine Learning for Creativity and Design."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Xun Huang and Serge Belongie. 2017. Arbitrary style transfer in real-time with adaptive instance normalization. In ICCV. 1501--1510.  Xun Huang and Serge Belongie. 2017. Arbitrary style transfer in real-time with adaptive instance normalization. In ICCV. 1501--1510.","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_2_2_14_1","volume-title":"The relativistic discriminator: a key element missing from standard GAN. arXiv preprint arXiv:1807.00734","author":"Jolicoeur-Martineau Alexia","year":"2018","unstructured":"Alexia Jolicoeur-Martineau . 2018. The relativistic discriminator: a key element missing from standard GAN. arXiv preprint arXiv:1807.00734 ( 2018 ). Alexia Jolicoeur-Martineau. 2018. The relativistic discriminator: a key element missing from standard GAN. arXiv preprint arXiv:1807.00734 (2018)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2017.1355393"},{"key":"e_1_3_2_2_16_1","unstructured":"Sharon L Kennedy. 2007. Painting music: rhythm and movement in art. (2007).  Sharon L Kennedy. 2007. Painting music: rhythm and movement in art. (2007)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Kazuhiro Kobayashi Tomoki Toda Graham Neubig Sakriani Sakti and Satoshi Nakamura. 2014. Statistical singing voice conversion with direct waveform modification based on the spectrum differential. In ISCA.  Kazuhiro Kobayashi Tomoki Toda Graham Neubig Sakriani Sakti and Satoshi Nakamura. 2014. Statistical singing voice conversion with direct waveform modification based on the spectrum differential. In ISCA.","DOI":"10.21437\/Interspeech.2014-539"},{"key":"e_1_3_2_2_18_1","volume-title":"Learning linear transformations for fast arbitrary style transfer. arXiv:1808.04537","author":"Li Xueting","year":"2018","unstructured":"Xueting Li , Sifei Liu , Jan Kautz , and Ming-Hsuan Yang . 2018. Learning linear transformations for fast arbitrary style transfer. arXiv:1808.04537 ( 2018 ). Xueting Li, Sifei Liu, Jan Kautz, and Ming-Hsuan Yang. 2018. Learning linear transformations for fast arbitrary style transfer. arXiv:1808.04537 (2018)."},{"key":"e_1_3_2_2_19_1","unstructured":"Yijun Li Chen Fang Jimei Yang Zhaowen Wang Xin Lu and Ming-Hsuan Yang. 2017. Universal style transfer via feature transforms. In NeurIPS. 386--396.  Yijun Li Chen Fang Jimei Yang Zhaowen Wang Xin Lu and Ming-Hsuan Yang. 2017. Universal style transfer via feature transforms. In NeurIPS. 386--396."},{"key":"e_1_3_2_2_20_1","volume-title":"Play as You Like: Timbre-enhanced Multi-modal Music Style Transfer. arXiv preprint arXiv:1811.12214","author":"Lu Chien-Yu","year":"2018","unstructured":"Chien-Yu Lu , Min-Xin Xue , Chia-Che Chang , Che-Rung Lee , and Li Su. 2018. Play as You Like: Timbre-enhanced Multi-modal Music Style Transfer. arXiv preprint arXiv:1811.12214 ( 2018 ). Chien-Yu Lu, Min-Xin Xue, Chia-Che Chang, Che-Rung Lee, and Li Su. 2018. Play as You Like: Timbre-enhanced Multi-modal Music Style Transfer. arXiv preprint arXiv:1811.12214 (2018)."},{"key":"e_1_3_2_2_21_1","unstructured":"Wei Tsung Lu and Li Su. 2018. Transferring the Style of Homophonic Music Using Recurrent Neural Networks and Autoregressive Model.. In ISMIR. 740--746.  Wei Tsung Lu and Li Su. 2018. Transferring the Style of Homophonic Music Using Recurrent Neural Networks and Autoregressive Model.. In ISMIR. 740--746."},{"key":"e_1_3_2_2_22_1","unstructured":"A Maezawa. 2018. Deep piano performance rendering with conditional VAE. In ISMIR Late Breaking and Demo Papers.  A Maezawa. 2018. Deep piano performance rendering with conditional VAE. In ISMIR Late Breaking and Demo Papers."},{"key":"e_1_3_2_2_23_1","volume-title":"Neural translation of musical style. arXiv preprint arXiv:1708.03535","author":"Malik Iman","year":"2017","unstructured":"Iman Malik and Carl Henrik Ek. 2017. Neural translation of musical style. arXiv preprint arXiv:1708.03535 ( 2017 ). Iman Malik and Carl Henrik Ek. 2017. Neural translation of musical style. arXiv preprint arXiv:1708.03535 (2017)."},{"key":"e_1_3_2_2_24_1","volume-title":"Visualizing Music: Tonal Progressions and Distributions.. In ISMIR. Citeseer, 189--194.","author":"Mardirossian Arpi","year":"2007","unstructured":"Arpi Mardirossian and Elaine Chew . 2007 . Visualizing Music: Tonal Progressions and Distributions.. In ISMIR. Citeseer, 189--194. Arpi Mardirossian and Elaine Chew. 2007. Visualizing Music: Tonal Progressions and Distributions.. In ISMIR. Citeseer, 189--194."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2010.05.006"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.2307\/1578702"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"#cr-split#-e_1_3_2_2_28_1.1","doi-asserted-by":"crossref","unstructured":"F. Schroff D. Kalenichenko and J. Philbin. 2015. FaceNet: A unified embedding for face recognition and clustering. In CVPR. 815--823. https:\/\/doi.org\/10.1109\/CVPR.2015.7298682 10.1109\/CVPR.2015.7298682","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"#cr-split#-e_1_3_2_2_28_1.2","doi-asserted-by":"crossref","unstructured":"F. Schroff D. Kalenichenko and J. Philbin. 2015. FaceNet: A unified embedding for face recognition and clustering. In CVPR. 815--823. https:\/\/doi.org\/10.1109\/CVPR.2015.7298682","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_2_29_1","unstructured":"Tianxiao Shen Tao Lei Regina Barzilay and Tommi Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. In NeurIPS. 6830--6841.  Tianxiao Shen Tao Lei Regina Barzilay and Tommi Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. In NeurIPS. 6830--6841."},{"key":"e_1_3_2_2_30_1","volume-title":"Avatar-net: Multi-scale zero-shot style transfer by feature decoration. In CVPR. 8242--8250.","author":"Sheng Lu","year":"2018","unstructured":"Lu Sheng , Ziyi Lin , Jing Shao , and Xiaogang Wang . 2018 . Avatar-net: Multi-scale zero-shot style transfer by feature decoration. In CVPR. 8242--8250. Lu Sheng, Ziyi Lin, Jing Shao, and Xiaogang Wang. 2018. Avatar-net: Multi-scale zero-shot style transfer by feature decoration. In CVPR. 8242--8250."},{"key":"e_1_3_2_2_31_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 1409.1556 (09","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 1409.1556 (09 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 1409.1556 (09 2014)."},{"key":"e_1_3_2_2_32_1","volume-title":"Neural style transfer for audio spectograms. arXiv preprint arXiv:1801.01589","author":"Verma Prateek","year":"2018","unstructured":"Prateek Verma and Julius O Smith . 2018. Neural style transfer for audio spectograms. arXiv preprint arXiv:1801.01589 ( 2018 ). Prateek Verma and Julius O Smith. 2018. Neural style transfer for audio spectograms. arXiv preprint arXiv:1801.01589 (2018)."},{"key":"e_1_3_2_2_33_1","unstructured":"Chia-Hung Wan Shun-Po Chuang and Hung-Yi Lee. 2019. Towards Audio to Scene Image Synthesis Using Generative Adversarial Network. In ICASSP. 496--500.  Chia-Hung Wan Shun-Po Chuang and Hung-Yi Lee. 2019. Towards Audio to Scene Image Synthesis Using Generative Adversarial Network. In ICASSP. 496--500."},{"key":"e_1_3_2_2_34_1","volume-title":"Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks. arXiv preprint arXiv:1807.02254","author":"Wu Cheng-Wei","year":"2018","unstructured":"Cheng-Wei Wu , Jen-Yu Liu , Yi-Hsuan Yang , and Jyh-Shing R Jang . 2018. Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks. arXiv preprint arXiv:1807.02254 ( 2018 ). Cheng-Wei Wu, Jen-Yu Liu, Yi-Hsuan Yang, and Jyh-Shing R Jang. 2018. Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks. arXiv preprint arXiv:1807.02254 (2018)."},{"key":"e_1_3_2_2_35_1","volume-title":"Self-attention generative adversarial networks. arXiv preprint arXiv:1805.08318","author":"Zhang Han","year":"2018","unstructured":"Han Zhang , Ian Goodfellow , Dimitris Metaxas , and Augustus Odena . 2018. Self-attention generative adversarial networks. arXiv preprint arXiv:1805.08318 ( 2018 ). Han Zhang, Ian Goodfellow, Dimitris Metaxas, and Augustus Odena. 2018. Self-attention generative adversarial networks. arXiv preprint arXiv:1805.08318 (2018)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Hang Zhao Chuang Gan Andrew Rouditchenko Carl Vondrick Josh McDermott and Antonio Torralba. 2018. The sound of pixels. In ECCV. 570--586.  Hang Zhao Chuang Gan Andrew Rouditchenko Carl Vondrick Josh McDermott and Antonio Torralba. 2018. The sound of pixels. In ECCV. 570--586.","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Yipin Zhou Zhaowen Wang Chen Fang Trung Bui and Tamara L Berg. 2018. Visual to sound: Generating natural sound for videos in the wild. In CVPR. 3550--3558.  Yipin Zhou Zhaowen Wang Chen Fang Trung Bui and Tamara L Berg. 2018. Visual to sound: Generating natural sound for videos in the wild. In CVPR. 3550--3558.","DOI":"10.1109\/CVPR.2018.00374"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"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\/3394171.3413624","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:15Z","timestamp":1750193235000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413624"}},"subtitle":["Cross-modal Style Transfer from Music to Visual Arts"],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":39,"alternative-id":["10.1145\/3394171.3413624","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413624","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"}}]}}