{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:05:37Z","timestamp":1780052737770,"version":"3.54.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Development Fund of Macau","award":["0071\/2022\/A"],"award-info":[{"award-number":["0071\/2022\/A"]}]},{"name":"Science and Technology Development Fund of Macau","award":["0095\/2023\/RIA2"],"award-info":[{"award-number":["0095\/2023\/RIA2"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3362149","type":"journal-article","created":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T18:40:08Z","timestamp":1707158408000},"page":"7250-7264","source":"Crossref","is-referenced-by-count":17,"title":["TA2V: Text-Audio Guided Video Generation"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3632-4167","authenticated-orcid":false,"given":"Minglu","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2664-4413","authenticated-orcid":false,"given":"Wenmin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7719-8364","authenticated-orcid":false,"given":"Tongbao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6589-2510","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4341-6474","authenticated-orcid":false,"given":"Ruochen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186752"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3295094"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3295098"},{"key":"ref5","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020"},{"key":"ref6","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref8","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref9","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref10","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022"},{"key":"ref11","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref12","article-title":"Godiva: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref14","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref15","article-title":"TrumerAI: Dreaming music with styleGAN","author":"Jeong","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00622"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083257"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref19","article-title":"Music2Video: Automatic generation of music video with fusion of audio and text","author":"Kim","year":"2022"},{"key":"ref20","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412890"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412698"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_42"},{"key":"ref31","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref32","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Oord","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref34","first-page":"16890","article-title":"Cogview2: Faster and better text-to-image generation via hierarchical transformers","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ding","year":"2022"},{"key":"ref35","first-page":"17","article-title":"Generating video from single image and sound","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Tsuchiya","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01768"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3262180"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612667"},{"key":"ref41","article-title":"Generative disco: Text-to-video generation for music visualization","author":"Liu","year":"2023"},{"key":"ref42","article-title":"Aadiff: Audio-aligned video synthesis with text-to-image diffusion","author":"Lee","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00719"},{"key":"ref44","article-title":"Any-to-any generation via composable diffusion","volume":"36","author":"Tang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28486"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref47","article-title":"Video diffusion models","author":"Ho","year":"2022"},{"key":"ref48","article-title":"Dreamix: Video diffusion models are general","author":"Molad","year":"2023"},{"key":"ref49","article-title":"Video-P2P: Video editing with cross-attention control","author":"Liu","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref51","article-title":"Soundini: Sound-guided diffusion for natural video editing","author":"Lee","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref53","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.3"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_25"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.146"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP48831.2020.9287124"},{"key":"ref61","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref62","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref63","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018"},{"key":"ref64","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref66","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref69","article-title":"CIFAR-10 (Canadian Institute for Advanced Research)","author":"Krizhevsky","year":"2010"},{"key":"ref70","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015"},{"key":"ref71","article-title":"Nice: Non-linear independent components estimation","author":"Dinh","year":"2014"},{"key":"ref72","article-title":"Density estimation using real NVP","author":"Dinh","year":"2016"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10420468.pdf?arnumber=10420468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:51:59Z","timestamp":1714762319000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10420468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3362149","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}