{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T06:38:16Z","timestamp":1777963096076,"version":"3.51.4"},"reference-count":57,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160101"],"award-info":[{"award-number":["2022ZD0160101"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Shanghai Natural Science Foundation","doi-asserted-by":"publisher","award":["23ZR1402900"],"award-info":[{"award-number":["23ZR1402900"]}],"id":[{"id":"10.13039\/100007219","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\/iccv51701.2025.02149","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23145-23155","source":"Crossref","is-referenced-by-count":1,"title":["SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Lin","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Future Information Technology, Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianfang","family":"Zeng","sequence":"additional","affiliation":[{"name":"StepFun,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kangcong","family":"Li","sequence":"additional","affiliation":[{"name":"College of Future Information Technology, Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Yu","sequence":"additional","affiliation":[{"name":"StepFun,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Future Information Technology, Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref4","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00670"},{"key":"ref8","article-title":"Benchmarking and improving detail image caption","author":"Dong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref9","article-title":"vila -2: Vila augmented vila","author":"Fang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","article-title":"The capacity for moral self-correction in large language models","author":"Ganguli","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref11","article-title":"Glore: When, where, and how to improve 11 m reasoning via global and local refinements","author":"Havrilla","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.331"},{"key":"ref13","article-title":"A topic-level self-correctional approach to mitigate hallucinations in mllms","author":"He","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref15","article-title":"Graph-based captioning: Enhancing visual descriptions by interconnecting region captions","author":"Hsieh","year":"2024","journal-title":"arXiv preprint arXiv"},{"issue":"2","key":"ref16","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","volume":"1","author":"Edward","year":"2022"},{"key":"ref17","article-title":"Large language models cannot self-correct reasoning yet","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref19","article-title":"When can 11 ms actually correct their own mistakes? a critical survey of self-correction of 11 ms","author":"Kamoi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","article-title":"Training language models to self-correct via reinforcement learning","author":"Kumar","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.395"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.205"},{"key":"ref23","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":"ref24","first-page":"19730","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":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.398"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref27","article-title":"Playground v3: Improving text-toimage alignment with deep-fusion large language models","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11197"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref31","article-title":"Omnicaptioner: One captioner to rule them all","author":"Yiting","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_17"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00660"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"ref37","article-title":"Is moral self-correction an innate capability of large language models? a mechanistic analysis to self-correction","author":"Qi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref38","article-title":"Recursive introspection: Teaching language model agents how to self-improve","author":"Yuxiao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","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":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref41","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00668"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_5"},{"key":"ref45","article-title":"Novelseek: When agent becomes the scientist-building closed-loop system from hypothesis to verification","author":"Team","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02521"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref49","article-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref50","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":"ref51","article-title":"Caption anything: Interactive image description with diverse multimodal controls","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref52","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref53","article-title":"Generating sequences by learning to self-correct","author":"Welleck","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref54","article-title":"Painting with words: Elevating detailed image captioning with benchmark and alignment learning","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ye","year":"2025"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1056"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"}],"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\/11444638.pdf?arnumber=11444638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:24:33Z","timestamp":1777613073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444638\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02149","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}