{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:13:20Z","timestamp":1777889600867,"version":"3.51.4"},"reference-count":42,"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 R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0161100"],"award-info":[{"award-number":["2022ZD0161100"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.01400","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15086-15095","source":"Crossref","is-referenced-by-count":0,"title":["HPSv3: Towards Wide-Spectrum Human Preference Score"],"prefix":"10.1109","author":[{"given":"Yuhang","family":"Ma","sequence":"first","affiliation":[{"name":"Mizzen AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoshi","family":"Wu","sequence":"additional","affiliation":[{"name":"CUHK MMLab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keqiang","family":"Sun","sequence":"additional","affiliation":[{"name":"Mizzen AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"CUHK MMLab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"1 [dev]: 12b-parameter open-source text-to-image diffusion model, 2024","journal-title":"Architecture: 12B-parameter diffusion model with T5-XXL text encoder; Features: Anatomically precise human generation, native multilingual support, commercial-grade text rendering; License: Non-commercial research use (Apache 2.0 with additional restrictions); Model Size: 23.8 GB FP16 weights"},{"key":"ref2","article-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"arXiv preprint arXiv","author":"Chen","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref4","author":"Chen","year":"2015","journal-title":"Microsoft COCO Captions: Data Collection and Evaluation Server"},{"key":"ref5","volume-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref6","author":"Fan","year":"2024","journal-title":"Fluid: Scaling autoregressive text-to-image generative models with continuous tokens"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01467"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref9","article-title":"Instantportrait: One-step portrait editing via diffusion multi-objective distillation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Lai","year":"2025"},{"key":"ref10","author":"Li","year":"2024","journal-title":"Playground v2.5: Three insights towards enhancing aesthetic quality in text-to-image generation"},{"key":"ref11","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref12","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref13","author":"Li","year":"2024","journal-title":"Ecnet: Effective controllable text-to-image diffusion models"},{"key":"ref14","author":"Li","year":"2024","journal-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32588"},{"key":"ref16","first-page":"3075","article-title":"New theory about light and colours","volume":"6","journal-title":"Philosophical Transactions of the Royal Society"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01536"},{"key":"ref18","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref19","article-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref20","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":"ref21","article-title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","author":"Ramesh","year":"2022","journal-title":"ArXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref23","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530738"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1188"},{"key":"ref27","author":"Sun","year":"2023","journal-title":"Journeydb: A benchmark for generative image understanding"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328912"},{"key":"ref29","author":"Sun","year":"2024","journal-title":"Genca: A textconditioned generative model for realistic and drivable codec avatars"},{"key":"ref30","author":"Sun","year":"2025","journal-title":"Probabilistic uncertain reward model"},{"key":"ref31","article-title":"Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref33","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref35","author":"Wu","year":"2023","journal-title":"Better Aligning Text-to-Image Models with Human Preference"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref37","first-page":"108","article-title":"Deep reward supervisions for tuning text-to-image diffusion models","volume-title":"European Conference on Computer Vision","author":"Wu","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01676"},{"key":"ref39","author":"Xu","year":"2023","journal-title":"ImageReward: Learning and Evaluating Human Preferences for Text-toImage Generation"},{"key":"ref40","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","author":"Zhang","year":"2024","journal-title":"Learning multidimensional human preference for text-to-image generation"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_1"}],"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\/11444113.pdf?arnumber=11444113","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:13:18Z","timestamp":1777612398000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444113\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01400","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}