{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:16:30Z","timestamp":1777889790639,"version":"3.51.4"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02084","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22447-22456","source":"Crossref","is-referenced-by-count":0,"title":["HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models"],"prefix":"10.1109","author":[{"given":"Zhixiang","family":"Wei","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangting","family":"Wang","sequence":"additional","affiliation":[{"name":"WeChat Vision, Tencent Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxiao","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Mei","sequence":"additional","affiliation":[{"name":"WeChat Vision, Tencent Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaian","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Jin","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengyun","family":"Rao","sequence":"additional","affiliation":[{"name":"WeChat Vision, Tencent Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref3","author":"Dong","year":"2024","journal-title":"Internlm-xcomposer: Mastering free-form textimage composition and comprehension in vision-language large model"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1544"},{"key":"ref6","author":"Fang","year":"2023","journal-title":"Data filtering networks"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref8","author":"Fu","year":"2024","journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models"},{"key":"ref9","author":"Yitzhak Gadre","year":"2023","journal-title":"Datacomp: In search of the next generation of multimodal datasets"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3059"},{"key":"ref11","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Open-clip","author":"Ilharco","year":"2021","journal-title":"If you use this software, please cite it as below"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_7"},{"key":"ref14","author":"Li","year":"2023","journal-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2132"},{"key":"ref17","article-title":"What if we recaption billions of web images with llama-3?","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref20","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref23","article-title":"Improving multimodal datasets with image captioning","volume":"36","author":"Nguyen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"In ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00559"},{"key":"ref27","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref29","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3695"},{"key":"ref33","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref35","article-title":"Demystifying clip data","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","author":"Yu","year":"2022","journal-title":"Coca: Contrastive captioners are image-text foundation models"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01330"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref39","article-title":"When and why visionlanguage models behave like bags-of-words, and what to do about it?","volume-title":"In International Conference on Learning Representations","author":"Yuksekgonul"},{"key":"ref40","article-title":"A large-scale study of representation learning with the visual task adaptation benchmark","author":"Zhai","year":"2019","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446293.pdf?arnumber=11446293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:21:24Z","timestamp":1777612884000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02084","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}