{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:32:10Z","timestamp":1777865530223,"version":"3.51.4"},"reference-count":45,"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\/iccv51701.2025.01798","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19342-19352","source":"Crossref","is-referenced-by-count":0,"title":["Engage for All: Making Ordinary Image Descriptions Appealing Again!"],"prefix":"10.1109","author":[{"given":"Yuyan","family":"Chen","sequence":"first","affiliation":[{"name":"Cornell University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Southern California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhou","sequence":"additional","affiliation":[{"name":"Morgan Stanley Service Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghan","family":"Cao","sequence":"additional","affiliation":[{"name":"San Francisco State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Guan","sequence":"additional","affiliation":[{"name":"University of Warwick"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Yang","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingpei","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Warwick"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2024.048104"},{"key":"ref2","author":"Bai","year":"2023","journal-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond"},{"key":"ref3","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":"ref4","article-title":"Punny captions: Witty wordplay in image descriptions","author":"Chandrasekaran","year":"2017","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570431"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681332"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29736"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref11","article-title":"Flexcap: Generating rich, localized, and flexible captions in images","author":"Dwibedi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"7654","article-title":"Gem: generating engaging multimodal content","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","author":"Gao","year":"2024"},{"key":"ref13","author":"Glm","year":"2024","journal-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools"},{"key":"ref14","article-title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","author":"J","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00455"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01273"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref20","article-title":"Glac net: Glocal attention cascading networks for multi-image cued story generation","author":"Kim","year":"2018","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Dialogcc: Large-scale multi-modal dialogue dataset","author":"Lee","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","volume":"corr abs\/2305.03726","author":"Li","year":"2023","journal-title":"Otter: A multimodal model with in-context instruction tuning"},{"key":"ref23","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01303"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref26","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28203"},{"key":"ref30","article-title":"Improving multimodal datasets with image captioning","author":"Nguyen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00564"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00559"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00560"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01280"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.679"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1080\/01410096.2007.9995223"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3648151"},{"key":"ref39","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1083"},{"key":"ref41","article-title":"Exploring diverse in-context configurations for image captioning","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref42","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01247"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01258"},{"key":"ref45","author":"Zhu","year":"2023","journal-title":"Minigpt-4: Enhancing visionlanguage understanding with advanced large language models"}],"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\/11444732.pdf?arnumber=11444732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:26Z","timestamp":1777531586000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01798","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}