{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:24:54Z","timestamp":1783095894713,"version":"3.54.6"},"reference-count":81,"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 R&D Program of China","award":["2021YFE0206700"],"award-info":[{"award-number":["2021YFE0206700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401365"],"award-info":[{"award-number":["62401365"]}],"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":["62271312"],"award-info":[{"award-number":["62271312"]}],"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":["62225112"],"award-info":[{"award-number":["62225112"]}],"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":["62132006"],"award-info":[{"award-number":["62132006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Pujiang Program","award":["22PJ1407400"],"award-info":[{"award-number":["22PJ1407400"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3604905","type":"journal-article","created":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:31:31Z","timestamp":1756755091000},"page":"8145-8159","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Dimensional Quality Assessment for Text-to-3D Assets: Dataset and Model"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6916-5821","authenticated-orcid":false,"given":"Kang","family":"Fu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-4067","authenticated-orcid":false,"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-7938","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6377-4730","authenticated-orcid":false,"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1714-3206","authenticated-orcid":false,"given":"Jia","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9984","article-title":"Escaping Platos cave: 3D shape from adversarial rendering","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Henzler","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00154"},{"key":"ref3","article-title":"Dreamfusion: Text-to-3D using 2D diffusion","author":"Poole","year":"2022"},{"key":"ref4","first-page":"8406","article-title":"ProlificDreamer: High-fidelity and diverse text-to-3D generation with variational score distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2023"},{"key":"ref5","first-page":"5769","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Gulrajani","year":"2023"},{"key":"ref6","first-page":"6629","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.","volume":"30","author":"Heusel","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3664199"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3410052"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref11","article-title":"Genie","year":"2024"},{"key":"ref12","article-title":"Meshy","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"ref16","first-page":"36652","article-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","volume-title":"Proc. Neural Adv. neural Inf. Process. Syst.","volume":"36","author":"Kirstain","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref18","first-page":"15903","article-title":"ImageReward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xu","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00636"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-9119-8_5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647885"},{"key":"ref24","article-title":"Measuring the quality of text-to-video model outputs: Metrics and dataset","author":"Chivileva","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref27","first-page":"62352","article-title":"FETV: A benchmark for fine-grained evaluation of open-domain text-to-video generation","volume-title":"Proc. Adv. Neural Inf. Process. Sys.","author":"Liu","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680868"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/OJID.2024.3351089"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3250956"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2018.8351786"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB55706.2022.9828671"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547955"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.02017.x"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.903319"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3643817"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296925"},{"key":"ref38","first-page":"174","article-title":"A novel methodology for quality assessment of voxelized point clouds","volume-title":"Proc. SPIE","volume":"10752","author":"Torlig","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3340894"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949359"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3186894"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100282"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3350180"},{"key":"ref44","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":"ref45","article-title":"Understanding and evaluating human preferences for AI generated images with instruction tuning","author":"Wang","year":"2024"},{"key":"ref46","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022"},{"key":"ref47","article-title":"threestudio: A unified framework for 3D content generation","author":"Guo","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00423"},{"key":"ref49","article-title":"Methodology for the Subjective Assessment of the Quality of Television Pictures","year":"2002"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2426416"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.133"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS.2013.6674512"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2018.2816783"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2788206"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref59","article-title":"InternVid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023"},{"key":"ref60","first-page":"54015","article-title":"Q-align: Teaching LMMs for visual scoring via discrete text-defined levels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680939"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413804"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3270621"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-33618-3_37"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/SITIS.2016.130"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3550274"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02050"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681471"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00641"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78125-4_4"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00659"},{"key":"ref79","article-title":"The Kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11146508.pdf?arnumber=11146508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:44:37Z","timestamp":1763059477000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11146508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3604905","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}