{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T17:11:15Z","timestamp":1783185075117,"version":"3.54.6"},"reference-count":54,"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":["62206022,62276025,62476027"],"award-info":[{"award-number":["62206022,62276025,62476027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2253200026"],"award-info":[{"award-number":["2253200026"]}],"id":[{"id":"10.13039\/501100012226","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\/iccv51701.2025.01991","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21440-21449","source":"Crossref","is-referenced-by-count":1,"title":["OmniDiff: A Comprehensive Benchmark for Fine-Grained Image Difference Captioning"],"prefix":"10.1109","author":[{"given":"Yuan","family":"Liu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saihui","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saijie","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiabao","family":"Du","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shibei","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongzhen","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref4","volume-title":"Artstation - leading showcase platform for art and design"},{"key":"ref5","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","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":"ref7","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref8","year":"2018","journal-title":"Blender - a 3d modelling and rendering package"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1065"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.xinn.2025.101253"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-short.5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00275"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_7"},{"issue":"2","key":"ref15","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074803"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1436"},{"key":"ref18","article-title":"Mantis: Interleaved multi-image instruction tuning","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00210"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref22","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"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","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3218921"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3218921"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref30","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_24"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00198"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_34"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01338"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1182"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.735"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3268004"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3254162"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00263"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_18"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3365104"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.430"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref47","article-title":"Ccexpert: Advancing mllm capability in remote sensing change captioning with differenceaware integration and a foundational dataset","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20218"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681453"},{"key":"ref52","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Internv13: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3497338"}],"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\/11445437.pdf?arnumber=11445437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:01:43Z","timestamp":1777611703000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445437\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01991","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}