{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:23:37Z","timestamp":1775579017867,"version":"3.50.1"},"reference-count":63,"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":"National Key Research and Development Program of China","award":["2020AAA0106400"],"award-info":[{"award-number":["2020AAA0106400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2043"],"award-info":[{"award-number":["U21B2043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102419"],"award-info":[{"award-number":["62102419"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102416"],"award-info":[{"award-number":["62102416"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3262180","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T17:34:55Z","timestamp":1680543295000},"page":"141-153","source":"Crossref","is-referenced-by-count":9,"title":["Sounding Video Generator: A Unified Framework for Text-Guided Sounding Video Generation"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5438-2524","authenticated-orcid":false,"given":"Jiawei","family":"Liu","sequence":"first","affiliation":[{"name":"The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7299-6431","authenticated-orcid":false,"given":"Weining","family":"Wang","sequence":"additional","affiliation":[{"name":"The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sihan","family":"Chen","sequence":"additional","affiliation":[{"name":"The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinxin","family":"Zhu","sequence":"additional","affiliation":[{"name":"The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0903-9131","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"613","article-title":"Generating videos with scene dynamics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vondrick","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref3","article-title":"A good image generator is what you need for high-resolution video synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tian","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref5","article-title":"Godiva: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183394"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"},{"key":"ref13","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref14","first-page":"17022","article-title":"Hifi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref15","first-page":"3325","article-title":"Audeo: Audio generation for a silent performance video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Su","year":"2020"},{"key":"ref16","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":"ref17","first-page":"7025","article-title":"Contrastive learning of global and local video representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/9781108891530.013"},{"key":"ref19","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oord","year":"2017"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref21","first-page":"344","article-title":"Self-supervised visual planning with temporal skip connections","volume-title":"Proc. Conf. Robot Learn.","author":"Ebert","year":"2017"},{"key":"ref22","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035281"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"ref26","first-page":"14837","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Razavi","year":"2019"},{"key":"ref27","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5220\/0010241801010112"},{"key":"ref29","article-title":"Videogpt: Video generation using VQ-VAE and transformers","author":"Yan","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref31","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022"},{"key":"ref32","article-title":"Threedworld: A platform for interactive multi-modal physical simulation","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Gan","year":"2021"},{"key":"ref33","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475195"},{"key":"ref40","first-page":"2","article-title":"Taming visually guided sound generation","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Iashin","year":"2021"},{"key":"ref41","first-page":"14881","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref42","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref44","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alwassel","year":"2020"},{"key":"ref45","article-title":"Audiovisual slowfast networks for video recognition","author":"Xiao","year":"2020"},{"key":"ref46","article-title":"Cross-modal attention consistency for video-audio unsupervised learning","author":"Min","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01198-w"},{"key":"ref48","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2624140"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01331-0"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref54","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Kim","year":"2019"},{"key":"ref55","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref57","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref58","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref59","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-011-0841-3"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10091449.pdf?arnumber=10091449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:32:30Z","timestamp":1705026750000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10091449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3262180","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}