{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:52Z","timestamp":1777865332541,"version":"3.51.4"},"reference-count":44,"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\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00341514"],"award-info":[{"award-number":["RS-2024-00341514"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002642","name":"Korea University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002642","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\/iccv51701.2025.01848","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19872-19881","source":"Crossref","is-referenced-by-count":0,"title":["CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning"],"prefix":"10.1109","author":[{"given":"Kuniaki","family":"Saito","sequence":"first","affiliation":[{"name":"OMRON SINIC X"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwanyong","family":"Park","sequence":"additional","affiliation":[{"name":"University of Seoul"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsushi","family":"Hashimoto","sequence":"additional","affiliation":[{"name":"OMRON SINIC X"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshitaka","family":"Ushiku","sequence":"additional","affiliation":[{"name":"OMRON SINIC X"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"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 preprint"},{"issue":"2","key":"ref3","first-page":"3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee","year":"2005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0688"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"ref8","first-page":"712","article-title":"Lengthcontrollable image captioning","volume-title":"ECCV","author":"Deng"},{"key":"ref9","article-title":"Flexcap: Describe anything in images in controllable detail","author":"Dwibedi","year":"2024","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.986"},{"key":"ref13","article-title":"spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing","author":"Honnibal","year":"2017","journal-title":"To appear"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01745"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00275"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3131393"},{"key":"ref17","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR workshop on fine-grained visual categorization (FGVC)","author":"Khosla","year":"2011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref19","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref21","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref24","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref25","article-title":"Quark: Controllable text generation with reinforced unlearning","author":"Lu","year":"2022","journal-title":"NeurIPS, 35:27591\u201327609"},{"key":"ref26","article-title":"Analysis of diversity-accuracy tradeoff in image captioning","author":"Luo","year":"2020","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_17"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref30","article-title":"Adapterfusion: Nondestructive task composition for transfer learning","author":"Pfeiffer","year":"2020","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref33","article-title":"Theo Coombes, and Romain Beaumont","author":"Schuhmann","year":"2022","journal-title":"Laion coco: 600 m synthetic captions from laion2b-en"},{"key":"ref34","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.346"},{"key":"ref37","volume-title":"Caltech-ucsd birds-200\u20132011","author":"Wah","year":"2011"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25360"},{"key":"ref39","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013834"},{"key":"ref41","first-page":"23965","article-title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","volume-title":"ICML","author":"Wortsman"},{"key":"ref42","article-title":"xgen-mm (blip-3): A family of open large multimodal models","author":"Xue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"}],"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\/11444073.pdf?arnumber=11444073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:05Z","timestamp":1777529825000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01848","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}