{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:26Z","timestamp":1777865306582,"version":"3.51.4"},"reference-count":84,"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":["62472222,62306292"],"award-info":[{"award-number":["62472222,62306292"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20240080"],"award-info":[{"award-number":["BK20240080"]}],"id":[{"id":"10.13039\/501100004608","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\/iccv51701.2025.00639","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6797-6807","source":"Crossref","is-referenced-by-count":0,"title":["Cycle-Consistent Learning for Joint Layout-to-Image Generation and Object Detection"],"prefix":"10.1109","author":[{"given":"Xinhao","family":"Cai","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuxia","family":"Lai","sequence":"additional","affiliation":[{"name":"Communication University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gensheng","family":"Pei","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yazhou","family":"Yao","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Yolov4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref6","article-title":"Geodiffusion: Textprompted geometric control for object detection data generation","author":"Chen","year":"2023","journal-title":"I C L R"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00526"},{"key":"ref8","article-title":"Id-aligner: Enhancing identitypreserving text-to-image generation with reward feedback learning","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Layoutdiffuse: Adapting foundational diffusion models for layout-to-image generation","author":"Cheng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref14","first-page":"1801","article-title":"Temporal cycleconsistency learning","author":"Dwibedi","year":"2019","journal-title":"CVPR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25133"},{"key":"ref16","author":"Gal","year":"2022","journal-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion. arXiv preprint"},{"key":"ref17","article-title":"Yolox: Exceeding yolo series in 2021","author":"Ge","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00433"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01480"},{"key":"ref22","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref26","article-title":"Decoupled weight decay regularization","author":"Ilya","year":"2019","journal-title":"ICLR"},{"key":"ref27","article-title":"Highresolution complex scene synthesis with transformers","volume-title":"arXiv preprint","author":"Jahn","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref30","article-title":"Learning to discover cross-domain relations with generative adversarial networks","author":"Kim","year":"2017","journal-title":"ICML"},{"key":"ref31","article-title":"Variational diffusion models","author":"Kingma","year":"2021","journal-title":"NeurIPS, 34"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00194"},{"key":"ref33","article-title":"Controlnet++: Improving conditional controls with efficient consistency feedback","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01356"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01247"},{"key":"ref41","article-title":"Pseudo numerical methods for diffusion models on manifolds","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00898"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_19"},{"key":"ref45","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"arXiv preprint","author":"Meng","year":"2021"},{"key":"ref46","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref49","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML, pages 88218831"},{"key":"ref50","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref55","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00681"},{"key":"ref57","first-page":"22562265","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref58","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01063"},{"key":"ref61","article-title":"Gen2det: Generate to detect","author":"Suri","year":"2023","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16368"},{"key":"ref63","article-title":"Question answering and question generation as dual tasks","author":"Tang","year":"2017","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref65","article-title":"Efficient diffusion models for vision: A survey","author":"Ulhaq","year":"2022","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01503"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00140"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28363"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2400250"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00692"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01283"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref73","article-title":"Learning visual prior via generative pre-training","author":"Xie","year":"2024","journal-title":"NeurIPS"},{"key":"ref74","article-title":"Cyclenet: Rethinking cycle consistency in textguided diffusion for image manipulation","author":"Xu","year":"2024","journal-title":"NeurIPS, 36"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00761"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref78","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00878"},{"key":"ref81","first-page":"42098","article-title":"X-paste: Revisiting scalable copy-paste for instance segmentation using clip and stablediffusion","author":"Zhao","year":"2023","journal-title":"ICML"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.244"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"}],"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\/11445191.pdf?arnumber=11445191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:13:57Z","timestamp":1777529637000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445191\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00639","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}