{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T02:21:07Z","timestamp":1782181267825,"version":"3.54.5"},"reference-count":42,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2024,5,1]]},"DOI":"10.1587\/transfun.2023eap1059","type":"journal-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T22:28:39Z","timestamp":1692743319000},"page":"836-844","source":"Crossref","is-referenced-by-count":6,"title":["Dance-Conditioned Artistic Music Generation by Creative-GAN"],"prefix":"10.1587","volume":"E107.A","author":[{"given":"Jiang","family":"HUANG","sequence":"first","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianglin","family":"HUANG","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lifang","family":"YANG","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhulin","family":"TAO","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] I.J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, \u201cGenerative adversarial nets,\u201d Advances in Neural Information Processing Systems, vol.3, pp.2672-2680, 2014."},{"key":"2","unstructured":"[2] A. van den Oord, O. Vinyals, and K. Kavukcuoglu, \u201cNeural discrete representation learning,\u201d NIPS, pp.6309-6318, 2017."},{"key":"3","unstructured":"[3] PAYNE, CHRISTINE, \u201cMuseNet,\u201d OpenAI [EB\/OL]. openai.com\/blog\/musenet."},{"key":"4","unstructured":"[4] A. Roberts, J. Engel, C. Raffel, et al., \u201cA hierarchical latent vector model for learning longterm structure in music,\u201d International Conference on Machine Learning, PMLR, 2019."},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] H.W. Dong, W.Y. Hsiao, L.C. Yang, et al., \u201cMuseGAN: Multitrack sequential generative adversarial networks for symbolic music generation and accompaniment,\u201d AAAI Conference on Artificial Intelligence, 2017.","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"6","unstructured":"[6] L.C. Yang, S.Y. Chou, and Y.H. Yang, \u201cMidiNet: A convolutional generative adversarial network for symbolic-domain music generation,\u201d arXiv preprint arXiv:1703.10847, 2017. 10.48550\/arXiv.1703.10847"},{"key":"7","unstructured":"[7] A. van den Oord, S. Dieleman, H. Zen, K. Simonyan, O. Vinyals, A. Graves, N. Kalchbrenner, A. Senior, and K. Kavukcuoglu, \u201cWaveNet: A generative model for raw audio,\u201d ICLR, 2016."},{"key":"8","unstructured":"[8] C.Z.A. Huang, A. Vaswani, J. Uszkoreit, et al., \u201cMusic transformer,\u201d arXiv preprint arXiv:1809.04281, 2018. 10.48550\/arXiv.1809.04281"},{"key":"9","unstructured":"[9] P. Dhariwal, H. Jun, C. Payne, J.W. Kim, A. Radford, and I. Sutskever, \u201cJukebox: A generative model for music,\u201d arXiv preprint arXiv:2005.00341, 2020. 10.48550\/arXiv.2005.00341"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] T. Tang, J. Jia, and H. Mao, \u201cDance with melody: An LSTM-autoencoder approach to music-oriented dance synthesis,\u201d ACM Multimedia, pp.1598-1606, 2018. 10.1145\/3240508.3240526","DOI":"10.1145\/3240508.3240526"},{"key":"11","unstructured":"[11] P. Tendulkar, A. Das, A. Kembhavi, and D. Parikh, \u201cFeel the music: Automatically generating a dance for an input song,\u201d arXiv preprint arXiv:2006.11905, 2020. 10.48550\/arXiv.2006.11905"},{"key":"12","unstructured":"[12] B. Korbar, D. Tran, and L. Torresani, \u201cCo-training of audio and video representations from self-supervised temporal synchronization,\u201d arXiv preprint arXiv:1807.00230, 2018."},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] M. Cardle, L. Barthe, S. Brooks, and P. Robinson, \u201cMusic-driven motion editing: Local motion transformations guided by music analysis,\u201d Proc. 20th Eurographics UK Conference, IEEE, pp.38-44, 2002. 10.1109\/eguk.2002.1011270","DOI":"10.1145\/1242073.1242235"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] M. Lee, K. Lee, and J. Park, \u201cMusic similarity-based approach to generating dance motion sequence,\u201d Multimed. Tools Appl., vol.62, no.3, pp.895-912, 2013. 10.1007\/s11042-012-1288-5","DOI":"10.1007\/s11042-012-1288-5"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] D. Holden, J. Saito, and T. Komura, \u201cA deep learning framework for character motion synthesis and editing,\u201d ACM Trans. Graph., voo.35, no.4, pp.1-11, 2016. 10.1145\/2897824.2925975","DOI":"10.1145\/2897824.2925975"},{"key":"16","unstructured":"[16] H.-Y. Lee, X. Yang, M.-Y. Liu, T.-C. Wang, Y.-D. Lu, M.-H. Yang, and J. Kautz, \u201cDancing to music,\u201d NeurIPS, 2019."},{"key":"17","unstructured":"[17] J. Li, Y. Yin, H. Chu, Y. Zhou, T. Wang, S. Fidler, and H. Li, \u201cLearning to generate diverse dance motions with transformer,\u201d ArXiv, abs\/2008.08171, 2020. 10.48550\/arXiv.2008.08171"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] H. Zhao, C. Gan, W.-C. Ma, and A. Torralba, \u201cThe sound of motions,\u201d ICCV, 2019. 10.1109\/iccv.2019.00182","DOI":"10.1109\/ICCV.2019.00182"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] S. Di, Z. Jiang, S. Liu, Z. Wang, L. Zhu, Z. He, H. Liu, and S. Yan, \u201cVideo background music generation with controllable music transformer,\u201d ACMMM, pp.2037-2045, 2021. 10.1145\/3474085.3475195","DOI":"10.1145\/3474085.3475195"},{"key":"20","unstructured":"[20] V. Iashin and E. Rahtu, \u201cTaming visually guided sound generation,\u201d British Machine Vision Conference (BMVC), 2021."},{"key":"21","unstructured":"[21] A. Razavi, A. van den Oord, and O. Vinyals, \u201cGenerating diverse high-fifidelity images with VQ-VAE-2,\u201d NIPS, 2019."},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] P. Esser, R. Rombach, and B. Ommer, \u201cTaming transformers for high-resolution image synthesis,\u201d CVPR, 2021. 10.1109\/cvpr46437.2021.01268","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"23","unstructured":"[23] M. Mirza and S. Osindero, \u201cConditional generative adversarial nets,\u201d arXiv preprint arXiv:1411.1784, 2014. 10.48550\/arXiv.1411.1784"},{"key":"24","unstructured":"[24] A. Elgammal, B. Liu, M. Elhoseiny, and M. Mazzone, \u201cCAN: Creative adversarial networks, generating \u201cart\u201d by learning about styles and deviating from style norms,\u201d arXiv preprint arXiv:1706.07068, 2017. 10.48550\/arXiv.1706.07068"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] J. Kim, H. Oh, S. Kim, H. Tong and S. Lee, \u201cA brand new dance partner: Music-conditioned pluralistic dancing controlled by multiple dance genres,\u201d CVPR, 2022. 10.1109\/cvpr52688.2022.00348","DOI":"10.1109\/CVPR52688.2022.00348"},{"key":"26","doi-asserted-by":"publisher","unstructured":"[26] L. Wang, Y. Xiong, Z. Wang, Y. Qiao, D. Lin, X. Tang, and L. Van Gool, \u201cTemporal segment networks for action recognition in videos,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.41, no.11, pp.2740-2755, 2018. 10.1109\/TPAMI.2018.2868668","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"27","doi-asserted-by":"publisher","unstructured":"[27] M. Loper, N. Mahmood, J. Romero, G. Pons-Moll, and M.J. Black, \u201cSMPL: A skinned multi-person linear model,\u201d ACM Trans. Graphic, vol.34, no.6, pp.1-16, 2015. 10.1145\/2816795.2818013","DOI":"10.1145\/2816795.2818013"},{"key":"28","unstructured":"[28] A.B.L. Larsen, S.K. S\u00f8nderby, H. Larochelle, and O. Winther, \u201cAutoencoding beyond pixels using a learned similarity metric,\u201d International Conference on Machine Learning, PMLR, 2016."},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] Y. Aytar, C. Vondrick, and A. Torralba, \u201cSoundNet: Learning sound representations from unlabeled video,\u201d NIPS, pp.892-900, 2016.","DOI":"10.1109\/CVPR.2016.18"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] R. Girshick, J. Donahue, T. Darrell, and J. Malik, \u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.580-587, 2014. 10.1109\/cvpr.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] R. Li, S. Yang, D.A. Ross, and A. Kanazawa, \u201cAI choreographer: Music conditioned 3D dance generation with AIST++,\u201d ICCV, 2021. 10.1109\/iccv48922.2021.01315","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] N. Mahmood, N. Ghorbani, N.F. Troje, G. Pons-Moll, and M.J. Black, \u201cAMASS: Archive of motion capture as surface shapes,\u201d Proc. IEEE International Conference on Computer Vision, pp.5442-5451, 2019. 10.1109\/iccv.2019.00554","DOI":"10.1109\/ICCV.2019.00554"},{"key":"33","doi-asserted-by":"publisher","unstructured":"[33] C. Ionescu, D. Papava, V. Olaru, and C. Sminchisescu, \u201cHuman3.6M: Large scale datasets and predictive methods for 3D human sensing in natural environments,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.36, no.7, pp.1325-1339, July 2014. 10.1109\/tpami.2013.248","DOI":"10.1109\/TPAMI.2013.248"},{"key":"34","unstructured":"[34] O. Alemi, J. Fran\u00e7oise, and P. Pasquier, \u201cGrooVenet: Real-time music-driven dance movement generation using artifificial neural networks,\u201d Networks, vol.8, no.17, 26, 2017."},{"key":"35","unstructured":"[35] W. Zhuang, C. Wang, S. Xia, J. Chai, and Y. Wang, \u201cMusic2Dance: Music-driven dance generation using wavenet,\u201d arXiv preprint arXiv:2002.03761, 2020."},{"key":"36","unstructured":"[36] T. Sainburg, timsainb\/noisereduce: v1.0.1; 2019. https:\/\/github.com\/timsainb\/noisereduce. Available from: https:\/\/doi.org\/10.5281\/zenodo.3243589 10.5281\/zenodo.3243589"},{"key":"37","unstructured":"[37] C.-T. Lin and M. Yang, \u201cInverseMV: Composing piano scores with a convolutional video-music transformer,\u201d ISMIR, 2020."},{"key":"38","unstructured":"[38] G. Aggarwal and D. Parikh, \u201cDance2Music: Automatic dance-driven music generation,\u201d arXiv preprint arXiv:2107.06252, 2021. 10.48550\/arXiv.2107.06252"},{"key":"39","doi-asserted-by":"crossref","unstructured":"[39] C. Gan, D. Huang, P. Chen, J.B. Tenenbaum, and A. Torralba, \u201cFoley music: Learning to generate music from videos,\u201d ECCV, pp.758-775, 2020. 10.1007\/978-3-030-58621-8_44","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"40","doi-asserted-by":"crossref","unstructured":"[40] Y. Zhu, K. Olszewski, Y. Wu, P. Achlioptas, M. Chai, Y. Yan, and S. Tulyakov, \u201cQuantized GAN for complex music generation from dance videos,\u201d ECCV, pp.182-199, 2022. 10.1007\/978-3-031-19836-6_11","DOI":"10.1007\/978-3-031-19836-6_11"},{"key":"41","doi-asserted-by":"crossref","unstructured":"[41] S. Hershey, S. Chaudhuri, D.P.W. Ellis, J.F. Gemmeke, A. Jansen, R.C. Moore, M. Plakal, D. Platt, R.A. Saurous, B. Seybold, M. Slaney, R.J. Weiss, and K. Wilson, \u201cCNN architectures for large-scale audio classification,\u201d ICASSP, IEEE, 2017. 10.1109\/icassp.2017.7952132","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"42","doi-asserted-by":"crossref","unstructured":"[42] J.F. Gemmeke, D.P.W. Ellis, D. Freedman, A. Jansen, W. Lawrence, R.C. Moore, M. Plakal, and M. Ritter, \u201cAudio set: An ontology and humanlabeled dataset for audio events,\u201d ICASSP, IEEE, 2017. 10.1109\/icassp.2017.7952261","DOI":"10.1109\/ICASSP.2017.7952261"}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E107.A\/5\/E107.A_2023EAP1059\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T03:21:43Z","timestamp":1714792903000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E107.A\/5\/E107.A_2023EAP1059\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,1]]},"references-count":42,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2023eap1059","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"value":"0916-8508","type":"print"},{"value":"1745-1337","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,1]]},"article-number":"2023EAP1059"}}