{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:03:08Z","timestamp":1777888988659,"version":"3.51.4"},"reference-count":52,"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\/iccv51701.2025.01402","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15107-15116","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Panoptic Scene Graph for Evaluating Fine-Grained Text-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Xueqing","family":"Deng","sequence":"first","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linjie","family":"Yang","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qihang","family":"Yu","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglin","family":"Yang","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang-Chieh","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.142"},{"key":"ref3","article-title":"PixArt-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"ICLR","author":"Chen","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"ref6","article-title":"Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-image generation","author":"Cho","year":"2024","journal-title":"ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02065"},{"key":"ref8","article-title":"Coconut-pancap: Joint panoptic segmentation and grounded captions for fine-grained understanding and generation","author":"Deng","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref9","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"ACL"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"arxiv preprint arxiv","author":"Esser","year":"2024"},{"key":"ref11","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref12","first-page":"113","volume":"13","author":"Gao","year":"2010","journal-title":"A survey of graph edit distance. Pattern Analysis and Applications"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01741"},{"key":"ref15","article-title":"Evalmuse-40k: A reliable and fine-grained benchmark with comprehensive human annotations for text-to-image generation model evaluation","author":"Han","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref17","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021209"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"ref20","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref21","article-title":"Ella: Equip diffusion models with 11 m for enhanced semantic alignment","author":"Hu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref25","volume-title":"Flux","year":"2024"},{"key":"ref26","article-title":"Graph edit distance: A new binary linear programming formulation","author":"Lerouge","year":"2015","journal-title":"arxiv preprint arxiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00538"},{"key":"ref28","article-title":"Naturalbench: Evaluating vision-language models on natural adversarial samples","author":"Li","year":"2025","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"ref30","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02652"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref33","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2025"},{"key":"ref34","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref35","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref38","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref39","article-title":"Improving image captioning with better use of captions","author":"Shi","year":"2020","journal-title":"ACL"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref41","article-title":"Diffusiondb: A large-scale prompt gallery dataset for text-toimage generative models","author":"Wang","year":"2023","journal-title":"ACL"},{"key":"ref42","article-title":"Revisiting text-to-image evaluation with gecko: On metrics, prompts, and human ratings","author":"Wiles","year":"2025","journal-title":"ICLR"},{"key":"ref43","article-title":"Human preference score v 2: A solid benchmark for evaluating human preferences of text-to-image synthesis","volume-title":"arxiv preprint arxiv","author":"Wu","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_11"},{"key":"ref45","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref46","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"TMLR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref48","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","author":"Yu","year":"2023","journal-title":"NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00742"},{"key":"ref51","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref52","article-title":"Scene graph generation: A comprehensive survey","author":"Zhu","year":"2022","journal-title":"arxiv preprint arxiv"}],"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\/11445744.pdf?arnumber=11445744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:04:26Z","timestamp":1777611866000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01402","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}