{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:21Z","timestamp":1777865481641,"version":"3.51.4"},"reference-count":61,"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\/iccv51701.2025.01879","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20204-20214","source":"Crossref","is-referenced-by-count":0,"title":["ROVI: A VLM-LLM Re-Captioned Dataset for Open-Vocabulary Instance-Grounded Text-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Cihang","family":"Peng","sequence":"first","affiliation":[{"name":"State Key Lab of CAD & CG, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiming","family":"Hou","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD & CG, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong","family":"Ren","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD & CG, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD & CG, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","author":"Bar-Tal","year":"2023","journal-title":"Multidiffusion: Fusing diffusion paths for controlled image generation"},{"key":"ref3","author":"Byeon","year":"2022","journal-title":"Coyo-700m: Image-text pair dataset."},{"key":"ref4","author":"Cai","year":"2024","journal-title":"Internlm2 technical report"},{"key":"ref5","volume-title":"Pixart- \u0251: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref9","author":"Bevan","year":"2023","journal-title":"Laion pop: 600,000 high-resolution images with detailed descriptions."},{"key":"ref10","author":"Dubey","year":"2024","journal-title":"The llama 3 herd of models"},{"key":"ref11","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00454"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.6"},{"key":"ref14","author":"Team","year":"2024","journal-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref16","author":"Guo","year":"2025","journal-title":"Deepseek-rl: Incentivizing reasoning capability in 11 ms via reinforcement learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01650"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref21","year":"2024","journal-title":"Flux."},{"key":"ref22","first-page":"1973019742","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref24","author":"Li","year":"2024","journal-title":"Autoregressive image generation without vector quantization"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref26","author":"Li","year":"2024","journal-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref30","article-title":"Scaling open-vocabulary object detection","volume":"36","author":"Minderer","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","author":"Onoe","year":"2024","journal-title":"Docci: Descriptions of connected and contrasting images"},{"key":"ref32","year":"2023","journal-title":"Gpt-4v(ision) system card."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref35","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"ref37","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":"ref38","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh","year":"2021"},{"key":"ref39","author":"Rombach","year":"2022","journal-title":"Stable diffusion v1.4 checkpoint."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","year":"2022","journal-title":"Laion-aesthetics"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref44","author":"Singla","year":"2024","journal-title":"From pixels to prose: A large dataset of dense image captions"},{"key":"ref45","author":"Sun","year":"2024","journal-title":"Autoregressive model beats diffusion: Llama for scalable image generation"},{"key":"ref46","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref47","author":"Wang","year":"2024","journal-title":"Ov-dino: Unified open-vocabulary detection with language-aware selective fusion"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01817"},{"key":"ref49","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref50","author":"Wang","year":"2023","journal-title":"Cogvlm: Visual expert for pretrained language models"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref52","author":"Wu","year":"2024","journal-title":"Ifadapter: Instance feature control for grounded text-to-image generation"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref54","author":"Yang","year":"2024","journal-title":"Qwen2 technical report"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02586"},{"issue":"3","key":"ref56","volume":"2","author":"Yu","year":"2022","journal-title":"Scaling autoregressive models for content-rich text-to-image generation"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref59","author":"Zhao","year":"2023","journal-title":"Improving pseudo labels for open-vocabulary object detection"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00651"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"}],"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\/11445890.pdf?arnumber=11445890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:39:47Z","timestamp":1777531187000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445890\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01879","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}