{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T14:46:53Z","timestamp":1730213213975,"version":"3.28.0"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,16]]},"DOI":"10.1109\/cvpr52733.2024.02533","type":"proceedings-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T17:34:53Z","timestamp":1726508093000},"page":"26816-26825","source":"Crossref","is-referenced-by-count":0,"title":["MELFuSION: Synthesizing Music from Image and Language Cues Using Diffusion Models"],"prefix":"10.1109","author":[{"given":"Sanjoy","family":"Chowdhury","sequence":"first","affiliation":[{"name":"Adobe Research"}]},{"given":"Sayan","family":"Nag","sequence":"additional","affiliation":[{"name":"University of Toronto"}]},{"given":"K J","family":"Joseph","sequence":"additional","affiliation":[{"name":"Adobe Research"}]},{"given":"Balaji Vasan","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Adobe Research"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}]}],"member":"263","reference":[{"journal-title":"Musiclm: Generating music from text","year":"2023","author":"Agostinelli","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10379"},{"journal-title":"Scaling instruction-finetuned language models","year":"2022","author":"Won Chung","key":"ref3"},{"journal-title":"Simple and controllable music generation","year":"2023","author":"Copet","key":"ref4"},{"journal-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","year":"2023","author":"Dai","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.05.151"},{"journal-title":"Jukebox: A gen-erative model for music","author":"Dhariwal","key":"ref7"},{"article-title":"Musegan: Multi-track sequential generative adversar-ial networks for symbolic music generation and accompani-ment","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Dong","key":"ref8"},{"journal-title":"An image is worth 16x16 words: Trans-formers for image recognition at scale","author":"Dosovitskiy","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00209.2012"},{"volume-title":"Riffusion-stable diffusion for real-time music generation","year":"2022","author":"Forsgren","key":"ref12"},{"key":"ref13","first-page":"9216","article-title":"An image is worth more than a thousand words: Towards disentanglement in the wild","volume":"34","author":"Gabbay","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"758","DOI":"10.1007\/978-3-030-58621-8_44","article-title":"Foley music: Learning to gen-erate music from videos","volume-title":"Computer Vision-ECCV 2020: 16th European Conference","author":"Gan","year":"2020"},{"journal-title":"Vampnet: Music generation via masked acous-tic token modeling","year":"2023","author":"Flores Garcia","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"journal-title":"Text-to-audio generation using instruction-tuned llm and latent diffusion model","year":"2023","author":"Ghosal","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1037\/pmu0000033"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"journal-title":"Mulan: A joint em-bedding of music audio and natural language","year":"2022","author":"Huang","key":"ref20"},{"journal-title":"Noise2music: Text-conditioned music generation with diffusion models","year":"2023","author":"Huang","key":"ref21"},{"journal-title":"Noise2music: Text-conditioned music generation with diffusion models","year":"2023","author":"Huang","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/577"},{"volume-title":"Generspeech: Towards style transfer for generaliz-able out-of-domain text-to-speech synthesis","year":"2022","author":"Huang","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref26","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fi-delity speech synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kong","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"journal-title":"Audiogen: Textually guided audio gen-eration","year":"2022","author":"Kreuk","key":"ref28"},{"volume-title":"Bddm: Bilateral denoising diffusion models for fast and high-quality speech synthesis","year":"2022","author":"Lam","key":"ref29"},{"journal-title":"Efficient neural music generation","year":"2023","author":"Lam","key":"ref30"},{"journal-title":"Priorgrad: Improving conditional denoising diffusion models with data-dependent adaptive prior","year":"2021","author":"Lee","key":"ref31"},{"journal-title":"Audi-oldm: Text-to-audio generation with latent diffusion models","year":"2023","author":"Liu","key":"ref32"},{"journal-title":"Contrastive audio-language learning for music","year":"2022","author":"Manco","key":"ref33"},{"volume-title":"2023 Mubert Inc. Mubert","year":"2023","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16117"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-019-0410-7"},{"key":"ref37","first-page":"8599","article-title":"Grad-tts: A diffusion prob-abilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov","year":"2021"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"journal-title":"The basic elements of music. Connexions","year":"2012","author":"Schmidt-Jones","key":"ref41"},{"journal-title":"Mousai: Text-to-music generation with long-context latent diffusion","year":"2023","author":"Schneider","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096023"},{"journal-title":"Denoising diffusion implicit models","year":"2020","author":"Song","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2013.788039"},{"key":"ref46","volume":"30","author":"Van","year":"2017","journal-title":"Advances in neural information pro-cessing systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroscience.2013.06.021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"journal-title":"Midinet: A convolutional generative adversarial network for symbolic-domain music generation","year":"2017","author":"Yang","key":"ref50"},{"key":"ref51","article-title":"A study on lstm networks for polyphonic music sequence modelling","author":"Ycart","year":"2017","journal-title":"ISMIR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1196\/annals.1284.001"}],"event":{"name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2024,6,16]]},"location":"Seattle, WA, USA","end":{"date-parts":[[2024,6,22]]}},"container-title":["2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10654794\/10654797\/10657460.pdf?arnumber=10657460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T05:58:49Z","timestamp":1726811929000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10657460\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,16]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/cvpr52733.2024.02533","relation":{},"subject":[],"published":{"date-parts":[[2024,6,16]]}}}