{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:37:36Z","timestamp":1781109456756,"version":"3.54.1"},"reference-count":70,"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\/iccv51701.2025.02189","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23582-23592","source":"Crossref","is-referenced-by-count":1,"title":["CompCap: Improving Multimodal Large Language Models with Composite Captions"],"prefix":"10.1109","author":[{"given":"Xiaohui","family":"Chen","sequence":"first","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satya Narayan","family":"Shukla","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahmoud","family":"Azab","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aashu","family":"Singh","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Yang","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ShengYun","family":"Peng","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanchao","family":"Yu","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shen","family":"Yan","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuewen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baosheng","family":"He","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref4","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","author":"Bradski","year":"2000","journal-title":"The OpenCV Library. Dr. Dobb\u2019s Journal of Software Tools"},{"key":"ref7","volume-title":"gapminder: Data from Gapminder","author":"Bryan","year":"2023"},{"key":"ref8","article-title":"Carbon","year":"2024","journal-title":"Carbon: Create and share beautiful images of your source code"},{"key":"ref9","article-title":"Mapqa: A dataset for question answering on choropleth maps","author":"Chang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.343"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref13","author":"Clark","year":"2015","journal-title":"Pillow (pil fork) documentation"},{"key":"ref14","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref17","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Eurostat","year":"2024","journal-title":"Eurostat: Statistical office of the european union"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41682-8_24"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"},{"key":"ref23","article-title":"Plotly Technologies Inc","year":"2015","journal-title":"Collaborative data science"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref26","article-title":"Figureqa: An annotated figure dataset for visual reasoning","author":"Ebrahimi Kahou","year":"2017","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref29","author":"Mermaid","year":"2024","journal-title":"Generation of diagrams and flowcharts from text"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref32","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref33","article-title":"Blip-2 : Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","article-title":"Clevr-math: A dataset for compositional language, visual and mathematical reasoning","author":"Lindstr\u00f6m","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023","journal-title":"ArXiv, abs\/2310.03744"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref39","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref40","article-title":"On the hidden mystery of ocr in large multimodal models","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref43","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref48","article-title":"Mm1: Methods, analysis & insights from multimodal 11 m pre-training","author":"McKinzie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref51","article-title":"Orca: Progressive learning from complex explanation traces of gpt4","author":"Mukherjee","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","year":"2023","journal-title":"4v (ision) system card"},{"issue":"5","key":"ref53","volume":"2","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref54","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref56","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal 11 ms","author":"Tong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","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":"ref60","article-title":"xgen-mm (blip-3): A family of open large multimodal models","author":"Xue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"List items one by one: A new data source and learning paradigm for multimodal 11 ms","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"ref65","article-title":"Mm -vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.51"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.622"},{"key":"ref69","article-title":"Omchat: A recipe to train multimodal language models with strong long context and video understanding","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Lima: Less is more for alignment","author":"Zhou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11445724.pdf?arnumber=11445724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:43Z","timestamp":1777529743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445724\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02189","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}