{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:46Z","timestamp":1777888846171,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222608,62276186,U23B2049,62172127,62436002"],"award-info":[{"award-number":["62222608,62276186,U23B2049,62172127,62436002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00203","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2099-2109","source":"Crossref","is-referenced-by-count":0,"title":["DALIP: Distribution Alignment-Based Language-Image Pre-Training for Domain-Specific Data"],"prefix":"10.1109","author":[{"given":"Junjie","family":"Wu","sequence":"first","affiliation":[{"name":"Tianjin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangtao","family":"Xie","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaolin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qilong","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghua","family":"Hu","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peihua","family":"Li","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sen","family":"Xu","sequence":"additional","affiliation":[{"name":"Yancheng Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Publicly available clinical bert embeddings","author":"Alsentzer","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"key":"ref3","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref4","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","volume":"abs\/2412.05271","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref7","article-title":"Probabilistic language-image pre-training","author":"Chun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","first-page":"7694","article-title":"Hyperbolic image-text representations","author":"Desai","year":"2023","journal-title":"ICML"},{"key":"ref10","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_38"},{"key":"ref12","article-title":"Does clip benefit visual question answering in the medical domain as much as it does in the general domain","author":"Eslami","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref13","article-title":"DataComp: In search of the next generation of multimodal datasets","author":"Gadre","year":"2023","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01084"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02538"},{"key":"ref16","article-title":"Pl@ntnet-300k: a plant image dataset with high label ambiguity and a long-tailed distribution","author":"Garcin","year":"2021","journal-title":"NeurIPS Datasets and Benchmarks"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11174"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref21","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref22","article-title":"MIMIC-CXR: A large publicly available database of labeled chest radiographs","volume":"abs\/1901.07042","author":"Johnson","year":"2019","journal-title":"CoRR"},{"key":"ref23","first-page":"18661","article-title":"Supervised contrastive learning","author":"Khosla","year":"2020","journal-title":"NeurIPS"},{"key":"ref24","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref25","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref27","article-title":"C-CLIP: Multimodal continual learning for vision-language model","author":"Liu","year":"2025","journal-title":"ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref29","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2017","journal-title":"ICLR"},{"key":"ref30","first-page":"25037","article-title":"Text-to-concept (and back) via cross-model alignment","author":"Moayeri","year":"2023","journal-title":"ICML"},{"key":"ref31","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00334"},{"key":"ref34","volume-title":"Birds 525 species - image classification","author":"Piosenka","year":"2023"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.compeleceng.2019.04.011","article-title":"Identification of plant leaf diseases using a nine-layer deep convolutional neural network","volume":"76","author":"Geetha Ramani","year":"2019","journal-title":"Comput. Electr. Eng."},{"issue":"8","key":"ref36","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref38","volume-title":"Medicinal leaf dataset","author":"Roopashree","year":"2020"},{"key":"ref39","article-title":"LAION400 M: open dataset of clip-filtered 400 million image-text pairs","volume":"abs\/2111.02114","author":"Schuhmann","year":"2021","journal-title":"CoRR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5334\/cstp.200"},{"key":"ref41","article-title":"An image is worth 16\u00d716 words, what is a video worth?","author":"Sharir","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557067"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3371158.3371196"},{"key":"ref45","volume-title":"Annotated plankton images-data set for developing and evaluating classification methods","author":"Sosik","year":"2015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01836"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1214\/09-AOAS312"},{"key":"ref48","first-page":"3232","article-title":"Meta-Album: Multi-domain meta-dataset for few-shot image classification","author":"Ullah","year":"2022","journal-title":"NeurIPS"},{"key":"ref49","article-title":"Representation learning with contrastive predictive coding","volume":"abs\/1807.03748","author":"van den Oord","year":"2018","journal-title":"CoRR"},{"key":"ref50","volume-title":"inat challenge 2021-fgvc8","author":"Van Horn","year":"2021"},{"key":"ref51","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","author":"Wang","year":"2022","journal-title":"NeurIPS 2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1097\/CORR.0000000000001297"},{"key":"ref53","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00899"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02317"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00781"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.5040\/9798881817916.ch-004"},{"key":"ref62","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref63","article-title":"Arboretum: A large multimodal dataset enabling ai for biodiversity","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00273"},{"key":"ref65","article-title":"Data mixing laws: Optimizing data mixtures by predicting language modeling performance","volume":"abs\/2403.16952","author":"Ye","year":"2024","journal-title":"CoRR"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref68","article-title":"Investigating the catastrophic forgetting in multimodal large language models","author":"Zhai","year":"2023","journal-title":"CoRR"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01376-1"},{"key":"ref70","article-title":"Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref71","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","author":"Zhang","year":"2022","journal-title":"MLHC"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3449154"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.794"}],"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\/11443552.pdf?arnumber=11443552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:48Z","timestamp":1777611588000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00203","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}