{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:20:45Z","timestamp":1777890045342,"version":"3.51.4"},"reference-count":73,"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\/iccv51701.2025.02281","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24603-24614","source":"Crossref","is-referenced-by-count":0,"title":["Mixture-of-Scores: Robust Image-Text Data Valuation via Three Lines of Code"],"prefix":"10.1109","author":[{"given":"Sitong","family":"Wu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoru","family":"Tan","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukang","family":"Chen","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaofeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyao","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bei","family":"Yu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaya","family":"Jia","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1288812900","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"In International Conference on Machine Learning","author":"Li","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539248"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref4","first-page":"43344343","article-title":"Learning to reweight examples for robust deep learning","volume-title":"International conference on machine learning","author":"Ren","year":"2018"},{"key":"ref5","author":"Zhang","year":"2024","journal-title":"Continuous-multiple image outpainting in one-step via positional query and a diffusionbased approach"},{"key":"ref6","author":"Chang","year":"2024","journal-title":"What matters in detecting ai-generated videos like sora?"},{"key":"ref7","author":"Sun","year":"2023","journal-title":"Eva-clip: Improved training techniques for clip at scale"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3412004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25172"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01114"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01971"},{"key":"ref12","article-title":"Contextual image masking modeling via synergized contrasting without view augmentation for faster and better visual pretraining","volume-title":"In The Eleventh International Conference on Learning Representations","author":"Zhang","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01598"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0967"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01120"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref18","author":"Hao","year":"2024","journal-title":"Urbanvlp: A multigranularity vision-language pre-trained foundation model for urban indicator prediction"},{"key":"ref19","article-title":"Zero-cl: Instance and feature decorrelation for negative-free symmetric contrastive learning","volume-title":"In International Conference on Learning Representations","author":"Zhang","year":"2021"},{"key":"ref20","first-page":"87488763","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref21","author":"Jiang","year":"2020","journal-title":"Devil\u2019s in the detail: Graph-based key-point alignment and embedding for person re-id"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00904"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02838"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1559"},{"key":"ref26","author":"Zhang","year":"2023","journal-title":"Patchlevel contrasting without patch correspondence for accurate and dense contrastive representation learning"},{"key":"ref27","first-page":"41990","article-title":"Patch-level contrastive learning via positional query for visual pre-training","volume-title":"International Conference on Machine Learning","author":"Zhang","year":"2023"},{"key":"ref28","author":"Zheng","year":"2024","journal-title":"Dape: Data-adaptive positional encoding for length extrapolation"},{"key":"ref29","author":"Li","year":"2025","journal-title":"Motcoder: Elevating large language models with modular of thought for challenging programming tasks"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1609"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01610"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3557502"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1006"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01843"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3454647"},{"key":"ref36","author":"Schuhmann","year":"2021","journal-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00171"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02657"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref42","article-title":"Training deep neural networks on noisy labels with bootstrapping","volume":"abs\/1412.6596","author":"Reed","year":"2014","journal-title":"CoRR"},{"key":"ref43","first-page":"16001","article-title":"The diversified ensemble neural network","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102842"},{"key":"ref45","author":"Yang","year":"2022","journal-title":"Chinese clip: Contrastive vision-language pretraining in chinese"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.522"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref48","volume-title":"Coyo-700m: Image-text pair dataset","author":"Byeon","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/079017"},{"key":"ref50","author":"Li","year":"2024","journal-title":"Robocoder: Robotic learning from basic skills to general tasks with large language models"},{"key":"ref51","author":"Zhong","year":"2024","journal-title":"Lyra: An efficient and speech-centric framework for omni-cognition"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00275"},{"key":"ref53","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3345844"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6996"},{"key":"ref56","author":"Li","year":"2021","journal-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm"},{"key":"ref57","article-title":"Cr2pq: Continuous relative rotary positional query for dense visual representation learning","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Zhang"},{"key":"ref58","article-title":"Do not disturb me: Person reidentification under the interference of other pedestrians","volume-title":"In European Conference on Computer Vision (ECCV)","author":"Shizhen","year":"2020"},{"key":"ref59","author":"Li","year":"2023","journal-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref60","author":"Li","year":"2024","journal-title":"Quickllama: Query-aware inference acceleration for large language models"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3797"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02262"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00292"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref68","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref69","volume-title":"The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results","author":"Everingham"},{"key":"ref70","article-title":"Error-bounded correction of noisy labels","author":"Zheng","year":"2020","journal-title":"ICML\u201920. JMLR.org"},{"key":"ref71","article-title":"Meta-weight-net: Learning an explicit mapping for sample weighting","volume":"32","author":"Shu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"}],"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\/11443413.pdf?arnumber=11443413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:34Z","timestamp":1777613314000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443413\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02281","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}