{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:28:43Z","timestamp":1740122923900,"version":"3.37.3"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T00:00:00Z","timestamp":1691539200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T00:00:00Z","timestamp":1691539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.61977045"],"award-info":[{"award-number":["No.61977045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16385-8","type":"journal-article","created":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T13:02:41Z","timestamp":1691586161000},"page":"22837-22854","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Editing outdoor scenes with a large annotated synthetic dataset"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9826-9806","authenticated-orcid":false,"given":"Mingye","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suncheng","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhuo","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,9]]},"reference":[{"key":"16385_CR1","doi-asserted-by":"crossref","unstructured":"Abdal R, Qin Y, Wonka P (2019) Image2stylegan: how to embed images into the stylegan latent space? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp 4432\u20134441","DOI":"10.1109\/ICCV.2019.00453"},{"key":"16385_CR2","unstructured":"Chen X, Fan H, Girshick R, He K (2020) Improved baselines with momentum contrastive learning. Preprint at http:\/\/arxiv.org\/abs\/2003.04297"},{"key":"16385_CR3","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"16385_CR4","doi-asserted-by":"crossref","unstructured":"Gatys, LA, Ecker AS, Bethge M (2016) Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 2414\u20132423","DOI":"10.1109\/CVPR.2016.265"},{"key":"16385_CR5","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in Neural Information Processing Systems 27, vol 27. pp 2672\u20132680"},{"key":"16385_CR6","unstructured":"H\u00e4rk\u00f6nen E, Hertzmann A, Lehtinen J, Paris S (2020) Ganspace: Discovering interpretable gan controls. Adv Neural Inf Proces Syst 33"},{"key":"16385_CR7","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"16385_CR8","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu J-Y, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 1125\u20131134","DOI":"10.1109\/CVPR.2017.632"},{"key":"16385_CR9","unstructured":"Jahanian A, Chai L, Isola P (2020) On the \u201csteerability\u201d of generative adversarial networks. In: International Conference on Learning Representations"},{"key":"16385_CR10","doi-asserted-by":"crossref","unstructured":"Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 4401\u20134410","DOI":"10.1109\/CVPR.2019.00453"},{"key":"16385_CR11","doi-asserted-by":"crossref","unstructured":"Karras T, Laine S, Aittala M, Hellsten J, Lehtinen J, Aila T (2020) Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 8110\u20138119","DOI":"10.1109\/CVPR42600.2020.00813"},{"issue":"4","key":"16385_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2601097.2601101","volume":"33","author":"P-Y Laffont","year":"2014","unstructured":"Laffont P-Y, Ren Z, Tao X, Qian C, Hays J (2014) Transient attributes for high-level understanding and editing of outdoor scenes. ACM Trans Graph 33(4):1\u201311","journal-title":"ACM Trans Graph"},{"key":"16385_CR13","unstructured":"Northcutt CG, Athalye A, Mueller J (2021) Pervasive label errors in test sets destabilize machine learning benchmarks. Preprint at http:\/\/arxiv.org\/abs\/2103.14749"},{"key":"16385_CR14","doi-asserted-by":"crossref","unstructured":"Park T, Liu M-Y, Wang T-C, Zhu J-Y (2019) Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 2337\u20132346","DOI":"10.1109\/CVPR.2019.00244"},{"key":"16385_CR15","doi-asserted-by":"crossref","unstructured":"Patashnik O, Wu Z, Shechtman E, Cohen-Or D, Lischinski D (2021) Styleclip: text-driven manipulation of stylegan imagery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp 2085\u20132094","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"16385_CR16","doi-asserted-by":"crossref","unstructured":"Patterson G, Hays J (2012) Sun attribute database: discovering, annotating, and recognizing scene attributes. In: IEEE Conference on Computer Vision and Pattern Recognition. pp 2751\u20132758","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"16385_CR17","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J et\u00a0al (2021) Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. pp 8748\u20138763"},{"key":"16385_CR18","doi-asserted-by":"crossref","unstructured":"Richter SR, Hayder Z, Koltun V (2017) Playing for benchmarks. In: Proceedings of the IEEE International Conference on Computer Vision. pp 2213\u20132222","DOI":"10.1109\/ICCV.2017.243"},{"key":"16385_CR19","doi-asserted-by":"crossref","unstructured":"Ros G, Sellart L, Materzynska J, Vazquez D, Lopez AM (2016) The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 3234\u20133243","DOI":"10.1109\/CVPR.2016.352"},{"key":"16385_CR20","doi-asserted-by":"crossref","unstructured":"Shen Y, Gu J, Tang X, Zhou B (2020) Interpreting the latent space of gans for semantic face editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 9243\u20139252","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"16385_CR21","doi-asserted-by":"crossref","unstructured":"Shen Y, Zhou B (2021) Closed-form factorization of latent semantics in gans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"16385_CR22","doi-asserted-by":"crossref","unstructured":"Sun P, Kretzschmar H, Dotiwalla X, Chouard A, Patnaik V, Tsui P, Guo J, Zhou Y, Chai Y, Caine B et\u00a0al (2020) Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 2446\u20132454","DOI":"10.1109\/CVPR42600.2020.00252"},{"issue":"1","key":"16385_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/10867651.2002.10487550","volume":"7","author":"WB Thompson","year":"2002","unstructured":"Thompson WB, Shirley P, Ferwerda JA (2002) A spatial post-processing algorithm for images of night scenes. J Graphics Tools 7(1):1\u201312","journal-title":"J Graphics Tools"},{"issue":"4","key":"16385_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459838","volume":"40","author":"O Tov","year":"2021","unstructured":"Tov O, Alaluf Y, Nitzan Y, Patashnik O, Cohen-Or D (2021) Designing an encoder for stylegan image manipulation. ACM Trans Graph 40(4):1\u201314","journal-title":"ACM Trans Graph"},{"key":"16385_CR25","doi-asserted-by":"crossref","unstructured":"Xiang S, Fu Y, You G, Liu T (2020) Unsupervised domain adaptation through synthesis for person re-identification. In: IEEE International Conference on Multimedia and Expo. pp 1\u20136","DOI":"10.1109\/ICME46284.2020.9102822"},{"key":"16385_CR26","doi-asserted-by":"crossref","unstructured":"Xie, M., Liu, T., Fu, Y.: Gos: A large-scale annotated outdoor scene synthetic dataset. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3244\u20133248 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746768"},{"key":"16385_CR27","doi-asserted-by":"crossref","unstructured":"Xie M, Xiang S, Wang F, Liu T, Fu Y (2022) Spatial attention guided local facial attribute editing. 2022 IEEE International Conference on Multimedia and Expo (ICME). IEEE, pp 01\u201306","DOI":"10.1109\/ICME52920.2022.9859605"},{"key":"16385_CR28","doi-asserted-by":"crossref","unstructured":"Yang C, Shen Y, Zhou B (2021) Semantic hierarchy emerges in deep generative representations for scene synthesis. Int J Comput Vis 1\u201316","DOI":"10.1007\/s11263-020-01429-5"},{"key":"16385_CR29","first-page":"1887","volume":"31","author":"S Yao","year":"2018","unstructured":"Yao S, Hsu TMH, Zhu J-Y, Wu J, Torralba A, Freeman B, Tenenbaum J (2018) 3D-aware scene manipulation via inverse graphics. Adv Neural Inf Proces Syst 31:1887\u20131898","journal-title":"Adv Neural Inf Proces Syst"},{"key":"16385_CR30","unstructured":"Yu F, Seff A, Zhang Y, Song S, Funkhouser T, Xiao J (2015) Lsun: construction of a large-scale image dataset using deep learning with humans in the loop. Preprint at http:\/\/arxiv.org\/abs\/1506.03365"},{"issue":"8","key":"16385_CR31","doi-asserted-by":"publisher","first-page":"1546","DOI":"10.1109\/TPAMI.2014.2299799","volume":"36","author":"AR Zamir","year":"2014","unstructured":"Zamir AR, Shah M (2014) Image geo-localization based on multiplenearest neighbor feature matching usinggeneralized graphs. IEEE Trans Pattern Anal Mach Intell 36(8):1546\u20131558","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"16385_CR32","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2017","unstructured":"Zhou B, Lapedriza A, Khosla A, Oliva A, Torralba A (2017) Places: a 10 million image database for scene recognition. IEEE Trans Pattern Anal Mach Intell 40(6):1452\u20131464","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16385-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16385-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16385-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T13:28:00Z","timestamp":1708608480000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16385-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,9]]},"references-count":32,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["16385"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16385-8","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,8,9]]},"assertion":[{"value":"19 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 May 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}