{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:06:54Z","timestamp":1780949214359,"version":"3.54.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005089","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L252033"],"award-info":[{"award-number":["L252033"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236010"],"award-info":[{"award-number":["62236010"]}],"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":["62141608"],"award-info":[{"award-number":["62141608"]}],"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":["62576339"],"award-info":[{"award-number":["62576339"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3657433","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T21:01:10Z","timestamp":1769202070000},"page":"7833-7845","source":"Crossref","is-referenced-by-count":0,"title":["AITQE: An Adaptive Image\u2013Text Quality Enhancer for Scalable MLLM Pretraining"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3726-5295","authenticated-orcid":false,"given":"Han","family":"Huang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqi","family":"Huo","sequence":"additional","affiliation":[{"name":"Foundation Model Department, Beijing Baichuan Intelligent Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijia","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyu","family":"Lu","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2164-3577","authenticated-orcid":false,"given":"Shu","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingning","family":"Wang","sequence":"additional","affiliation":[{"name":"Foundation Model Department, Beijing Baichuan Intelligent Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9233-3827","authenticated-orcid":false,"given":"Qiang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weipeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Foundation Model Department, Beijing Baichuan Intelligent Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-8647","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref3","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref4","article-title":"DeepSeek-VL: Towards real-world vision-language understanding","author":"Lu","year":"2024","journal-title":"arXiv:2403.05525"},{"key":"ref5","article-title":"What matters when building vision-language models?","author":"Lauren\u00e7on","year":"2024","journal-title":"arXiv:2405.02246"},{"key":"ref6","article-title":"Building and better understanding vision-language models: Insights and future directions","author":"Lauren\u00e7on","year":"2024","journal-title":"arXiv:2408.12637"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_18"},{"key":"ref8","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal LLMs","author":"Tong","year":"2024","journal-title":"arXiv:2406.16860"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref10","article-title":"VILA2: VILA augmented VILA","author":"Fang","year":"2024","journal-title":"arXiv:2407.17453"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref13","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":"ref14","article-title":"InternLM-XComposer-2.5: A versatile large vision language model supporting long-contextual input and output","author":"Zhang","year":"2024","journal-title":"arXiv:2407.03320"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref16","article-title":"Data filtering networks","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Fang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref18","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Neural Inf. Process. Syst. (NIPS)","volume":"24","author":"Ord\u00f3\u00f1ez"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref21","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv:2111.02114"},{"key":"ref22","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref23","article-title":"Finetuned multimodal language models are high-quality image-text data filters","author":"Wang","year":"2024","journal-title":"arXiv:2403.02677"},{"key":"ref24","first-page":"370","article-title":"ShareGPT4V: Improving large multi-modal models with better captions","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Lin"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3220297"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424566"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3443197"},{"key":"ref28","article-title":"Coyo-700m: Image-text pair dataset","author":"Byeon","year":"2022"},{"key":"ref29","article-title":"The devil is in the details: A deep dive into the rabbit hole of data filtering","author":"Yu","year":"2023","journal-title":"arXiv:2309.15954"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3653385"},{"key":"ref31","article-title":"Demystifying CLIP data","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref32","first-page":"27092","article-title":"DataComp: In search of the next generation of multimodal datasets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gadre"},{"key":"ref33","article-title":"T-MARS: Improving visual representations by circumventing text feature learning","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Maini"},{"key":"ref34","article-title":"CLIPLoss and norm-based data selection methods for multimodal contrastive learning","author":"Wang","year":"2024","journal-title":"arXiv:2405.19547"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3525158"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3343520"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3533205"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1544"},{"key":"ref40","first-page":"22047","article-title":"Improving multimodal datasets with image captioning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref41","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref42","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01330"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref47","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv:2306.13394"},{"key":"ref48","article-title":"AMBER: An LLM-free multi-dimensional benchmark for MLLMs hallucination evaluation","author":"Wang","year":"2023","journal-title":"arXiv:2311.07397"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1410"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11363249.pdf?arnumber=11363249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:37Z","timestamp":1780948477000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11363249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":54,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3657433","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}