{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:23:12Z","timestamp":1759450992767,"version":"build-2065373602"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0160803"],"award-info":[{"award-number":["2022ZD0160803"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106182"],"award-info":[{"award-number":["62106182"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3586119","type":"journal-article","created":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T13:29:51Z","timestamp":1751549391000},"page":"6732-6739","source":"Crossref","is-referenced-by-count":0,"title":["PIMG: Progressive Image-to-Music Generation With Contrastive Diffusion Models"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4634-3802","authenticated-orcid":false,"given":"Mulin","family":"Chen","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3778-6843","authenticated-orcid":false,"given":"Yajie","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475195"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01433"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISM55400.2022.00051"},{"article-title":"Mosai: Text-to-music generation with long-context latent diffusion","year":"2023","author":"Schneider","key":"ref4"},{"article-title":"Noise2music: Text-conditioned music generation with diffusion models","year":"2023","author":"Huang","key":"ref5"},{"article-title":"Msanii: High fidelity music synthesis on a shoestring budget","year":"2023","author":"Maina","key":"ref6"},{"article-title":"Musiclm: Generating music from text","year":"2023","author":"Agostinelli","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3338089"},{"key":"ref9","first-page":"103","article-title":"Music synthesis from images","volume-title":"Proc. Int. Conf. Comput. Creativity","author":"Santos","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE53005.2021.9622004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5860\/choice.45-4287"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/652"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011061"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29178"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3276177"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321495"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413671"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548084"},{"key":"ref21","article-title":"FIGARO: Controllable music generation using learned and expert features","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rtte","year":"2023"},{"key":"ref22","first-page":"47704","article-title":"Simple and controllable music generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Copet","year":"2024"},{"key":"ref23","first-page":"1376","article-title":"Museformer: Transformer with fine-and coarse-grained attention for music generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27810"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3284996"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/648"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3194957"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111159"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3025666"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3157148"},{"key":"ref32","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/02699930902975754"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3106813"},{"key":"ref35","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren","year":"2015"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref37","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"3","key":"ref40","first-page":"39","article-title":"International Affective Picture System (IAPS): Technical Manual and Affective Ratings","volume":"1","author":"Lang","year":"1997","journal-title":"NIMH Center Study Emotion Attention"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-013-0379-1"},{"key":"ref42","first-page":"318","article-title":"EMOPIA: A multi-modal pop piano dataset for emotion recognition and emotion-based music generation","author":"Hung","year":"2021"},{"key":"ref43","first-page":"109","article-title":"Music FaderNets: Controllable music generation based on high-level features via low-level feature modelling","volume-title":"Proc. Int. Soc. Music Inf.","author":"Tan","year":"2020"},{"key":"ref44","first-page":"142","article-title":"The jazz transformer on the front line: Exploring the shortcomings of ai-composed music through quantitative measures","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Wu","year":"2020"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11071375.pdf?arnumber=11071375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T04:34:47Z","timestamp":1759379687000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11071375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3586119","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}