{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T17:02:49Z","timestamp":1791046969261,"version":"4.1.0"},"reference-count":117,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62401365"],"award-info":[{"award-number":["62401365"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["BX20250411"],"award-info":[{"award-number":["BX20250411"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"crossref","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tcsvt.2026.3695960","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T19:37:35Z","timestamp":1779478655000},"page":"13708-13722","source":"Crossref","is-referenced-by-count":1,"title":["HarmonyQA: A Unified Framework for Harmonization Quality Assessment"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7834-6179","authenticated-orcid":false,"given":"Zitong","family":"Xu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University","place":["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","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangji","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1300-7401","authenticated-orcid":false,"given":"Liu","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9890-2698","authenticated-orcid":false,"given":"Jiarui","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7753-1596","authenticated-orcid":false,"given":"Sijing","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7337-1748","authenticated-orcid":false,"given":"Yunhao","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2936-6340","authenticated-orcid":false,"given":"Qingbo","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China","place":["Chengdu, 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","place":["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","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2143-7063","authenticated-orcid":false,"given":"Patrick","family":"Le Callet","sequence":"additional","affiliation":[{"name":"University of Nantes","place":["Nantes, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00573"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01814"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2043888"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409107"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01792"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612404"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25099"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612451"},{"key":"ref14","first-page":"10728","article-title":"Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2925550"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_40"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/172"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00409"},{"key":"ref19","article-title":"RelightVid: Temporal-consistent diffusion model for video relighting","author":"Fang","year":"2025","journal-title":"arXiv:2501.16330"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/38.946629"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.166"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141934"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882269"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778862"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185580"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.449"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref30","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","author":"Ho"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00574"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_25"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11209987"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2109730"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/83.841940"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859389"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00123"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2026.3651009"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521734"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2011.6190099"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2147325"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2191563"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2760518"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00026"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3509032"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2781420"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11209305"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2025.3627787"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01608"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755294"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2025.3627128"},{"key":"ref64","first-page":"46","article-title":"Aigciqa2023: A large-scale image quality assessment database for ai generated images: From the perspectives of quality","volume-title":"Proc. CAAI Int. Conf. Artif. Intell. (CAAI AI)","author":"Wang"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3616234"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00305"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01758"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249741"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00710"},{"key":"ref76","volume-title":"Methodology for the Subjective Assessment of the Quality of Television Pictures","year":"2012"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2175935"},{"key":"ref79","first-page":"1","article-title":"An improved full-reference image quality metric based on structure compensation","volume-title":"Proc. Conf. Asia\u2013Pacific Signal Inf. Process. Assoc. (APSIPA)","author":"Gu"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2293423"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2346028"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20221"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref84","article-title":"LLaVA-NeXT-interleave: Tackling multi-image, video, and 3D in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv:2407.07895"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref86","first-page":"98891","article-title":"mPLUG-Owl3: Towards long image-sequence understanding in multimodal large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ye"},{"key":"ref87","article-title":"InternLM-XComposer: A vision-language large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023","journal-title":"arXiv:2309.15112"},{"key":"ref88","volume-title":"Llama 3.2: Revolutionizing Edge AI and Vision With Open","year":"2024"},{"key":"ref89","article-title":"MiniCPM-V: A GPT-4 V level MLLM on your phone","author":"Yao","year":"2024","journal-title":"arXiv:2408.01800"},{"key":"ref90","article-title":"DeepSeek-VL: Towards real-world vision-language understanding","author":"Lu","year":"2024","journal-title":"arXiv:2403.05525"},{"key":"ref91","article-title":"DeepSeek-VL2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv:2412.10302"},{"key":"ref92","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025","journal-title":"arXiv:2502.13923"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.133"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_14"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455999"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00167"},{"key":"ref99","article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","author":"Lin","year":"2023","journal-title":"arXiv:2311.10122"},{"key":"ref100","article-title":"InternVideo2.5: Empowering video MLLMs with long and rich context modeling","author":"Wang","year":"2025","journal-title":"arXiv:2501.12386"},{"key":"ref101","article-title":"VideoLLaMA 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv:2501.13106"},{"key":"ref102","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","volume-title":"arXiv:2412.05271","author":"Chen","year":"2024"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32754"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref105","article-title":"InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025","journal-title":"arXiv:2504.10479"},{"key":"ref106","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024","journal-title":"arXiv:2412.05271"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1117\/1.3267105"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2014.10.009"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901772"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01380"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2042111"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11679504\/11534315.pdf?arnumber=11534315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:04:55Z","timestamp":1788807895000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11534315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":117,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3695960","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}