{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T03:49:37Z","timestamp":1782964177547,"version":"3.54.5"},"reference-count":65,"publisher":"Tsinghua University Press","issue":"2","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s41095-023-0356-2","type":"journal-article","created":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T23:45:05Z","timestamp":1704239105000},"page":"355-373","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Controllable multi-domain semantic artwork synthesis"],"prefix":"10.26599","volume":"10","author":[{"given":"Yuantian","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Tsukuba, Tsukuba 305-8577, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satoshi","family":"Iizuka","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Tsukuba, Tsukuba 305-8577, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edgar","family":"Simo-Serra","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Waseda University, Tokyo 169-8050, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuhiro","family":"Fukui","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Tsukuba, Tsukuba 305-8577, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"issue":"2","key":"356_CR1","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3390\/arts7020018","volume":"7","author":"A Hertzmann","year":"2018","unstructured":"Hertzmann, A. Can computers create art? Arts Vol. 7, No. 2, 18, 2018.","journal-title":"Arts"},{"key":"356_CR2","doi-asserted-by":"crossref","unstructured":"Gatys, L. A.; Ecker, A. S.; Bethge, M. Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2414\u20132423, 2016.","DOI":"10.1109\/CVPR.2016.265"},{"key":"356_CR3","doi-asserted-by":"crossref","unstructured":"Tan, W. R.; Chan, C. S.; Aguirre, H. E.; Tanaka, K. ArtGAN: Artwork synthesis with conditional categorical GANs. In: Proceedings of the IEEE International Conference on Image Processing, 3760\u20133764, 2017.","DOI":"10.1109\/ICIP.2017.8296985"},{"key":"356_CR4","unstructured":"Elgammal, A.; Liu, B.; Elhoseiny, M.; Mazzone, M. CAN: Creative adversarial networks, generating \u201cart\u201d by learning about styles and deviating from style norms. arXiv preprint arXiv:1706.07068, 2017."},{"key":"356_CR5","doi-asserted-by":"crossref","unstructured":"Zhu, J. Y.; Park, T.; Isola, P.; Efros, A. A. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, 2242\u20132251, 2017.","DOI":"10.1109\/ICCV.2017.244"},{"key":"356_CR6","doi-asserted-by":"crossref","unstructured":"Isola, P.; Zhu, J. Y.; Zhou, T. H.; Efros, A. A. Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5967\u20135976, 2017.","DOI":"10.1109\/CVPR.2017.632"},{"key":"356_CR7","first-page":"207","volume-title":"Computer Vision\u2013ACCV 2020. Lecture Notes in Computer Science, Vol. 12627","author":"B C Liu","year":"2021","unstructured":"Liu, B. C.; Song, K. P.; Zhu, Y. Z.; Elgammal, A. Sketch-to-art: Synthesizing stylized art images from sketches. In: Computer Vision\u2013ACCV 2020. Lecture Notes in Computer Science, Vol. 12627. Ishikawa, H.; Liu, C. L.; Pajdla, T.; Shi, J. Eds. Springer Cham, 207\u2013222, 2021."},{"key":"356_CR8","doi-asserted-by":"crossref","unstructured":"Men, Y. F.; Lian, Z. H.; Tang, Y. M.; Xiao, J. G. A common framework for interactive texture transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6353\u20136362, 2018.","DOI":"10.1109\/CVPR.2018.00665"},{"key":"356_CR9","unstructured":"Champandard, A. J. Semantic style transfer and turning two-bit doodles into fine artworks. arXiv preprint arXiv:1603.01768, 2016."},{"key":"356_CR10","doi-asserted-by":"crossref","unstructured":"Park, T.; Liu, M. Y.; Wang, T. C.; Zhu, J. Y. Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2332\u20132341, 2019.","DOI":"10.1109\/CVPR.2019.00244"},{"key":"356_CR11","unstructured":"Zhao, S. Y.; Cui, J.; Sheng, Y. L.; Dong, Y.; Liang, X.; Chang, E. I.; Xu, Y. Large scale image completion via co-modulated generative adversarial networks. arXiv preprint arXiv:2103.10428, 2021."},{"key":"356_CR12","unstructured":"Sushko, V.; Sch\u00f6nfeld, E.; Zhang, D.; Gall, J.; Schiele, B.; Khoreva, A. You only need adversarial supervision for semantic image synthesis. arXiv preprint arXiv:2012.04781, 2020."},{"key":"356_CR13","doi-asserted-by":"crossref","unstructured":"Zhu, Z.; Xu, Z. L.; You, A. S.; Bai, X. Semantically multi-modal image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5466\u20135475, 2020.","DOI":"10.1109\/CVPR42600.2020.00551"},{"key":"356_CR14","doi-asserted-by":"crossref","unstructured":"Zhu, P. H.; Abdal, R.; Qin, Y. P.; Wonka, P. SEAN: Image synthesis with semantic region-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5103\u20135112, 2020.","DOI":"10.1109\/CVPR42600.2020.00515"},{"key":"356_CR15","doi-asserted-by":"crossref","unstructured":"Hertzmann, A.; Jacobs, C. E.; Oliver, N.; Curless, B.; Salesin, D. H. Image analogies. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, 327\u2013340, 2001.","DOI":"10.1145\/383259.383295"},{"issue":"2","key":"356_CR16","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1080\/17513470701441445","volume":"1","author":"H Dehlinger","year":"2007","unstructured":"Dehlinger, H. On fine art and generative line drawings. Journal of Mathematics and the Arts Vol. 1, No. 2, 97\u2013111, 2007.","journal-title":"Journal of Mathematics and the Arts"},{"key":"356_CR17","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.procs.2012.09.112","volume":"13","author":"S Phon-Amnuaisuk","year":"2012","unstructured":"Phon-Amnuaisuk, S.; Panjapornpon, J. Controlling generative processes of generative art somnuk phon-. Procedia Computer Science Vol. 13, 43\u201352, 2012.","journal-title":"Procedia Computer Science"},{"issue":"11","key":"356_CR18","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative adversarial networks. Communications of the ACM Vol. 63, No. 11, 139\u2013144, 2020.","journal-title":"Communications of the ACM"},{"issue":"1","key":"356_CR19","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TIP.2018.2866698","volume":"28","author":"W R Tan","year":"2019","unstructured":"Tan, W. R.; Chan, C. S.; Aguirre, H. E.; Tanaka, K. Improved ArtGAN for conditional synthesis of natural image and artwork. IEEE Transactions on Image Processing Vol. 28, No. 1, 394\u2013409, 2019.","journal-title":"IEEE Transactions on Image Processing"},{"key":"356_CR20","unstructured":"Xue, A. End-to-end Chinese landscape painting creation using generative adversarial networks. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 3862\u20133870, 2023."},{"key":"356_CR21","doi-asserted-by":"crossref","unstructured":"Dobler, K.; H\u00fcbscher, F.; Westphal, J.; Sierra-M\u00fanera, A.; de Melo, G.; Krestel, R. Art creation with multi-conditional StyleGANs. arXiv preprint arXiv:2202.11777, 2022.","DOI":"10.24963\/ijcai.2022\/684"},{"key":"356_CR22","unstructured":"Ramesh, A.; Dhariwal, P.; Nichol, A.; Chu, C.; Chen, M. Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125, 2022."},{"key":"356_CR23","doi-asserted-by":"crossref","unstructured":"Rombach, R.; Blattmann, A.; Lorenz, D.; Esser, P.; Ommer, B. High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 10674\u201310685, 2022.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"356_CR24","unstructured":"Krizhevsky, A.; Sutskever, I.; Hinton, G. E. ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, Vol. 1, 1097\u20131105, 2012."},{"key":"356_CR25","unstructured":"Dumoulin, V.; Shlens, J.; Kudlur, M. A learned representation for artistic style. arXiv preprint arXiv:1610.07629, 2016."},{"key":"356_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y. H.; Wang, N. Y.; Liu, J. Y.; Hou, X. D. Demystifying neural style transfer. arXiv preprint arXiv:1701.01036, 2017.","DOI":"10.24963\/ijcai.2017\/310"},{"key":"356_CR27","unstructured":"Yin, R. J. Content aware neural style transfer. arXiv preprint arXiv:1601.04568, 2016."},{"key":"356_CR28","unstructured":"Gatys, L. A.; Bethge, M.; Hertzmann, A.; Shechtman, E. Preserving color in neural artistic style transfer. arXiv preprint arXiv:1606.05897, 2016."},{"key":"356_CR29","doi-asserted-by":"crossref","unstructured":"Kolkin, N.; Salavon, J.; Shakhnarovich, G. Style transfer by relaxed optimal transport and self-similarity. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 10043\u201310052, 2019.","DOI":"10.1109\/CVPR.2019.01029"},{"key":"356_CR30","unstructured":"Kusner, M. J.; Sun, Y.; Kolkin, N. I.; Weinberger, K. Q. From word embeddings to document distances. In: Proceedings of the 32nd International Conference on Machine Learning, 957\u2013966, 2015."},{"key":"356_CR31","doi-asserted-by":"crossref","unstructured":"Huang, X.; Belongie, S. Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, 1510\u20131519, 2017.","DOI":"10.1109\/ICCV.2017.167"},{"key":"356_CR32","doi-asserted-by":"crossref","unstructured":"Wang, T. C.; Liu, M. Y.; Zhu, J. Y.; Tao, A.; Kautz, J.; Catanzaro, B. High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8798\u20138807, 2018.","DOI":"10.1109\/CVPR.2018.00917"},{"key":"356_CR33","doi-asserted-by":"crossref","unstructured":"Yi, Z. L.; Zhang, H.; Tan, P.; Gong, M. L. DualGAN: Unsupervised dual learning for image-to-image translation. In: Proceedings of the IEEE International Conference on Computer Vision, 2868\u20132876, 2017.","DOI":"10.1109\/ICCV.2017.310"},{"key":"356_CR34","unstructured":"Hoffman, J.; Tzeng, E.; Park, T.; Zhu, J. Y.; Isola, P.; Saenko, K.; Efros, A. A.; Darrell, T. CyCADA: Cycle-consistent adversarial domain adaptation. In: Proceedings of the 35th International Conference on Machine Learning, 1989\u20131998, 2018."},{"key":"356_CR35","unstructured":"Zhu, J. Y.; Zhang, R.; Pathak, D.; Darrell, T.; Efros, A. A.; Wang, O.; Shechtman, E. Toward multimodal image-to-image translation. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 465\u2013476, 2017."},{"key":"356_CR36","first-page":"179","volume-title":"Computer Vision\u2013ECCV 2018. Lecture Notes in Computer Science, Vol. 11207","author":"X Huang","year":"2018","unstructured":"Huang, X.; Liu, M. Y.; Belongie, S.; Kautz, J. Multimodal unsupervised image-to-image translation. In: Computer Vision\u2013ECCV 2018. Lecture Notes in Computer Science, Vol. 11207. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 179\u2013196, 2018."},{"key":"356_CR37","first-page":"36","volume-title":"Computer Vision\u2013ECCV 2018. Lecture Notes in Computer Science, Vol. 11205","author":"H Y Lee","year":"2018","unstructured":"Lee, H. Y.; Tseng, H. Y.; Huang, J. B.; Singh, M.; Yang, M. H. Diverse image-to-image translation via disentangled representations. In: Computer Vision\u2013ECCV 2018. Lecture Notes in Computer Science, Vol. 11205. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 36\u201352, 2018."},{"issue":"10\u201311","key":"356_CR38","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1007\/s11263-019-01284-z","volume":"128","author":"H Y Lee","year":"2020","unstructured":"Lee, H. Y.; Tseng, H. Y.; Mao, Q.; Huang, J. B.; Lu, Y. D.; Singh, M.; Yang, M. H. DRIT++: Diverse image-to-image translation via disentangled representations. International Journal of Computer Vision Vol. 128, Nos. 10\u201311, 2402\u20132417, 2020.","journal-title":"International Journal of Computer Vision"},{"key":"356_CR39","doi-asserted-by":"crossref","unstructured":"Liu, M. Y.; Huang, X.; Mallya, A.; Karras, T.; Aila, T. M.; Lehtinen, J.; Kautz, J. Few-shot unsupervised image-to-image translation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 10550\u201310559, 2019.","DOI":"10.1109\/ICCV.2019.01065"},{"issue":"2","key":"356_CR40","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1109\/TIP.2018.2869695","volume":"28","author":"X Y Chen","year":"2019","unstructured":"Chen, X. Y.; Xu, C.; Yang, X. K.; Song, L.; Tao, D. C. Gated-GAN: Adversarial gated networks for multi-collection style transfer. IEEE Transactions on Image Processing Vol. 28, No. 2, 546\u2013560, 2019.","journal-title":"IEEE Transactions on Image Processing"},{"key":"356_CR41","first-page":"573","volume-title":"Computer Vision\u2013ECCV 2020. Lecture Notes in Computer Science, Vol. 12353","author":"H Y Chang","year":"2020","unstructured":"Chang, H. Y.; Wang, Z. X.; Chuang, Y. Y. Domain-specific mappings for generative adversarial style transfer. In: Computer Vision\u2013ECCV 2020. Lecture Notes in Computer Science, Vol. 12353. Vedaldi, A.; Bischof, H.; Brox, T.; Frahm, J. M. Eds. Springer Cham, 573\u2013589, 2020."},{"key":"356_CR42","unstructured":"Park, T.; Zhu, J.-Y.; Wang, O.; Lu, J.; Shechtman, E.; Efros, A. A.; Zhang, R. Swapping autoencoder for deep image manipulation. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, Article No. 604, 7198\u20137211, 2020."},{"key":"356_CR43","doi-asserted-by":"crossref","unstructured":"He, B.; Gao, F.; Ma, D. Q.; Shi, B. X.; Duan, L. Y. ChipGAN: A generative adversarial network for Chinese ink wash painting style transfer. In: Proceedings of the 26th ACM International Conference on Multimedia, 1172\u20131180, 2018.","DOI":"10.1145\/3240508.3240655"},{"issue":"4","key":"356_CR44","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L C Chen","year":"2018","unstructured":"Chen, L. C.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A. L. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 40, No. 4, 834\u2013848, 2018.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"356_CR45","unstructured":"Wang, T. C.; Liu, M. Y.; Zhu, J. Y.; Liu, G. L.; Tao, A.; Kautz, J.; Catanzaro, B. Video-to-video synthesis. arXiv preprint arXiv:1808.06601, 2018."},{"key":"356_CR46","doi-asserted-by":"crossref","unstructured":"Choi, Y.; Choi, M.; Kim, M.; Ha, J. W.; Kim, S.; Choo, J. StarGAN: Unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8789\u20138797, 2018.","DOI":"10.1109\/CVPR.2018.00916"},{"key":"356_CR47","doi-asserted-by":"crossref","unstructured":"Qi, X. J.; Chen, Q. F.; Jia, J. Y.; Koltun, V. Semi-parametric image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8808\u20138816, 2018.","DOI":"10.1109\/CVPR.2018.00918"},{"key":"356_CR48","doi-asserted-by":"crossref","unstructured":"Wang, M.; Yang, G. Y.; Li, R. L.; Liang, R. Z.; Zhang, S. H.; Hall, P. M.; Hu, S. M. Example-guided style-consistent image synthesis from semantic labeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1495\u20131504, 2019.","DOI":"10.1109\/CVPR.2019.00159"},{"issue":"1","key":"356_CR49","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s41095-019-0136-1","volume":"5","author":"S Y Zhang","year":"2019","unstructured":"Zhang, S. Y.; Liang, R. Z.; Wang, M. ShadowGAN: Shadow synthesis for virtual objects with conditional adversarial networks. Computational Visual Media Vol. 5, No. 1, 105\u2013115, 2019.","journal-title":"Computational Visual Media"},{"issue":"1","key":"356_CR50","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s41095-021-0203-2","volume":"7","author":"W Y Zhou","year":"2021","unstructured":"Zhou, W. Y.; Yang, G. W.; Hu, S. M. Jittor-GAN: A fast-training generative adversarial network model zoo based on Jittor. Computational Visual Media Vol. 7, No. 1, 153\u2013157, 2021.","journal-title":"Computational Visual Media"},{"issue":"2","key":"356_CR51","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s41095-022-0284-6","volume":"9","author":"C Wang","year":"2023","unstructured":"Wang, C.; Tang, F.; Zhang, Y.; Wu, T. R.; Dong, W. M. Towards harmonized regional style transfer and manipulation for facial images. Computational Visual Media Vol. 9, No. 2, 351\u2013366, 2023.","journal-title":"Computational Visual Media"},{"key":"356_CR52","doi-asserted-by":"crossref","unstructured":"Karras, T.; Laine, S.; Aittala, M.; Hellsten, J.; Lehtinen, J.; Aila, T. M. Analyzing and improving the image quality of StyleGAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8107\u20138116, 2020.","DOI":"10.1109\/CVPR42600.2020.00813"},{"issue":"2","key":"356_CR53","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1111\/cgf.14473","volume":"41","author":"N Cohen","year":"2022","unstructured":"Cohen, N.; Newman, Y.; Shamir, A. Semantic segmentation in art paintings. Computer Graphics Forum Vol. 41, No. 2, 261\u2013275, 2022.","journal-title":"Computer Graphics Forum"},{"key":"356_CR54","first-page":"740","volume-title":"Computer Vision - ECCV 2014. Lecture Notes in Computer Science, Vol. 8693","author":"T Y Lin","year":"2014","unstructured":"Lin, T. Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Doll\u00e1r, P.; Zitnick, C. L. Microsoft COCO: Common objects in context. In: Computer Vision - ECCV 2014. Lecture Notes in Computer Science, Vol. 8693. Fleet, D.; Pajdla, T.; Schiele, B.; Tuytelaars, T. Eds. Springer Cham, 740\u2013755, 2014."},{"issue":"3","key":"356_CR55","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B L Zhou","year":"2019","unstructured":"Zhou, B. L.; Zhao, H.; Puig, X.; Xiao, T. T.; Fidler, S.; Barriuso, A.; Torralba, A. Semantic understanding of scenes through the ADE20K dataset. International Journal of Computer Vision Vol. 127, No. 3, 302\u2013321, 2019.","journal-title":"International Journal of Computer Vision"},{"issue":"11","key":"356_CR56","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1109\/34.969114","volume":"23","author":"Y Boykov","year":"2001","unstructured":"Boykov, Y.; Veksler, O.; Zabih, R. Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 23, No. 11, 1222\u20131239, 2001.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"356_CR57","unstructured":"Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014."},{"key":"356_CR58","doi-asserted-by":"crossref","unstructured":"Xie, S. N.; Tu, Z. W. Holistically-nested edge detection. In: Proceedings of the IEEE International Conference on Computer Vision, 1395\u20131403, 2015.","DOI":"10.1109\/ICCV.2015.164"},{"key":"356_CR59","first-page":"369","volume-title":"Computer Vision\u2013ECCV 2020. Lecture Notes in Computer Science, Vol. 12356","author":"S Gu","year":"2020","unstructured":"Gu, S.; Bao, J.; Chen, D.; Wen, F. GIQA: Generated image quality assessment. In: Computer Vision\u2013ECCV 2020. Lecture Notes in Computer Science, Vol. 12356. Vedaldi, A.; Bischof, H.; Brox, T.; Frahm, J. M. Eds. Springer Cham, 369\u2013385, 2020."},{"key":"356_CR60","doi-asserted-by":"crossref","unstructured":"Fu, J.; Liu, J.; Tian, H. J.; Li, Y.; Bao, Y. J.; Fang, Z. W.; Lu, H. Q. Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3141\u20133149, 2019.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"356_CR61","doi-asserted-by":"crossref","unstructured":"Shen, Y. J.; Gu, J. J.; Tang, X. O.; Zhou, B. L. Interpreting the latent space of GANs for semantic face editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 9240\u20139249, 2020.","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"356_CR62","doi-asserted-by":"crossref","unstructured":"McInnes, L.; Healy, J.; Melville, J. UMAP: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426, 2018.","DOI":"10.21105\/joss.00861"},{"key":"356_CR63","first-page":"694","volume-title":"Computer Vision\u2013ECCV 2016. Lecture Notes in Computer Science, Vol. 9906","author":"J Johnson","year":"2016","unstructured":"Johnson, J.; Alahi, A.; Li, F. F. Perceptual losses for real-time style transfer and super-resolution. In: Computer Vision\u2013ECCV 2016. Lecture Notes in Computer Science, Vol. 9906. Leibe, B.; Matas, J.; Sebe, N.; Welling, M. Eds. Springer Cham, 694\u2013711, 2016."},{"key":"356_CR64","unstructured":"Kingma, D. P.; Welling, M. Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114, 2013."},{"key":"356_CR65","unstructured":"Heusel, M.; Ramsauer, H.; Unterthiner, T.; Nessler, B.; Hochreiter, S. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 6629\u20136640, 2017."}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-023-0356-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41095-023-0356-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-023-0356-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10897642\/10897652.pdf?arnumber=10897652","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:38:48Z","timestamp":1762367928000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10897652\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":65,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1007\/s41095-023-0356-2","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2024,4]]},"assertion":[{"value":"1 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no competing interests to declare that are relavent to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration of competing interest"}}]}}