{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T19:30:07Z","timestamp":1783711807920,"version":"3.55.0"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"8","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:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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":["61972068"],"award-info":[{"award-number":["61972068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976042"],"award-info":[{"award-number":["61976042"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s10489-024-05522-x","type":"journal-article","created":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T08:02:01Z","timestamp":1716192121000},"page":"6558-6578","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Unsupervised image-to-image translation with multiscale attention generative adversarial network"],"prefix":"10.1007","volume":"54","author":[{"given":"Fasheng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianyi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuming","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,20]]},"reference":[{"key":"5522_CR1","doi-asserted-by":"publisher","first-page":"3859","DOI":"10.1109\/TMM.2021.3109419","volume":"24","author":"Y Pang","year":"2022","unstructured":"Pang Y, Lin J, Qin T, Chen Z (2022) Image-to-image translation: Methods and applications. IEEE Trans Multimed 24:3859\u20133881. https:\/\/doi.org\/10.1109\/TMM.2021.3109419","journal-title":"IEEE Trans Multimed"},{"issue":"5","key":"5522_CR2","doi-asserted-by":"publisher","first-page":"2952","DOI":"10.1002\/int.22726","volume":"37","author":"D Wu","year":"2022","unstructured":"Wu D, Gan J, Zhou J, Wang J, Gao W (2022) Fine-grained semantic ethnic costume high-resolution image colorization with conditional gan. Int J Intell Syst 37(5):2952\u20132968","journal-title":"Int J Intell Syst"},{"key":"5522_CR3","doi-asserted-by":"crossref","unstructured":"Dekel T, Gan C, Krishnan D, Liu C, Freeman WT (2018) Sparse, smart contours to represent and edit images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3511\u20133520","DOI":"10.1109\/CVPR.2018.00370"},{"key":"5522_CR4","doi-asserted-by":"crossref","unstructured":"Ledig C, Theis L, Husz\u00e1r F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z et al (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4681\u20134690","DOI":"10.1109\/CVPR.2017.19"},{"key":"5522_CR5","unstructured":"Wang T-C, Liu M-Y, Zhu J-Y, Liu G, Tao A, Kautz J, Catanzaro B (2018) Video-to-video synthesis. arXiv preprint arXiv:1808.06601"},{"key":"5522_CR6","unstructured":"Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784"},{"key":"5522_CR7","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":"5522_CR8","doi-asserted-by":"crossref","unstructured":"Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223\u20132232","DOI":"10.1109\/ICCV.2017.244"},{"key":"5522_CR9","unstructured":"Benaim S, Wolf L (2017) One-sided unsupervised domain mapping. Adv Neural Inf Process Syst 752\u2013762"},{"key":"5522_CR10","doi-asserted-by":"crossref","unstructured":"Yi Z, Zhang H, Tan P, Gong M (2017) Dualgan: Unsupervised dual learning for image-to-image translation. In: Proceedings of the IEEE international conference on computer vision, pp 2849\u20132857","DOI":"10.1109\/ICCV.2017.310"},{"key":"5522_CR11","doi-asserted-by":"crossref","unstructured":"Sun Y, Lu Y, Lu H, Zhao Q, Wang S (2022) Multimodal unsupervised image-to-image translation without independent style encoder. In: Proceedings of the international conference on multimedia modeling, pp 624\u2013636","DOI":"10.1007\/978-3-030-98358-1_49"},{"key":"5522_CR12","unstructured":"Kim T, Cha M, Kim H, Lee JK, Kim J (2017) Learning to discover cross-domain relations with generative adversarial networks. In: International conference on machine learning, pp 1857\u20131865. PMLR"},{"issue":"4","key":"5522_CR13","doi-asserted-by":"publisher","first-page":"1972","DOI":"10.1109\/TNNLS.2021.3105725","volume":"34","author":"H Tang","year":"2023","unstructured":"Tang H, Liu H, Xu D, Torr PH, Sebe N (2023) Attentiongan: Unpaired image-to-image translation using attention-guided generative adversarial networks. IEEE Trans Neural Netw Learn Syst 34(4):1972\u20131987","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"5522_CR14","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1109\/TMM.2020.2975961","volume":"23","author":"H Emami","year":"2020","unstructured":"Emami H, Aliabadi MM, Dong M, Chinnam RB (2020) Spa-gan: Spatial attention gan for image-to-image translation. IEEE Trans Multimed 23:391\u2013401","journal-title":"IEEE Trans Multimed"},{"key":"5522_CR15","unstructured":"Kim J, Kim M, Kang H, Lee K (2020) U-gat-it: Unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. In: Proceedings of international conference on learning representations, pp 1\u201319"},{"issue":"15","key":"5522_CR16","doi-asserted-by":"publisher","first-page":"6858","DOI":"10.3390\/s23156858","volume":"23","author":"H-Y Lee","year":"2023","unstructured":"Lee H-Y, Li Y-H, Lee T-H, Aslam MS (2023) Progressively unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. Sensors 23(15):6858","journal-title":"Sensors"},{"issue":"17","key":"5522_CR17","doi-asserted-by":"publisher","first-page":"7338","DOI":"10.3390\/s23177338","volume":"23","author":"S Cheng","year":"2023","unstructured":"Cheng S, Wang L, Zhang M, Zeng C, Meng Y (2023) Sugan: A stable u-net based generative adversarial network. Sensors 23(17):7338. https:\/\/doi.org\/10.3390\/s23177338","journal-title":"Sensors"},{"key":"5522_CR18","doi-asserted-by":"crossref","unstructured":"Bae K, Kim H-I, Kwon Y, Moon J (2023) Unsupervised bidirectional style transfer network using local feature transform module. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 740\u2013749","DOI":"10.1109\/CVPRW59228.2023.00081"},{"key":"5522_CR19","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"},{"issue":"2","key":"5522_CR20","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"S-H Gao","year":"2019","unstructured":"Gao S-H, Cheng M-M, Zhao K, Zhang X-Y, Yang M-H, Torr P (2019) Res2net: A new multi-scale backbone architecture. IEEE Trans Pattern Anal Mach Intell 43(2):652\u2013662","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5522_CR21","doi-asserted-by":"publisher","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7132\u20137141. https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"5522_CR22","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS (2018) Cbam: Convolutional block attention module. In: Proceedings of the european conference on computer vision, pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"issue":"4","key":"5522_CR23","doi-asserted-by":"publisher","first-page":"3313","DOI":"10.1109\/TKDE.2021.3130191","volume":"35","author":"J Gui","year":"2023","unstructured":"Gui J, Sun Z, Wen Y, Tao D, Ye J (2023) A review on generative adversarial networks: Algorithms, theory, and applications. IEEE Trans Knowl Data Eng 35(4):3313\u20133332. https:\/\/doi.org\/10.1109\/TKDE.2021.3130191","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"5522_CR24","doi-asserted-by":"crossref","unstructured":"Lee KS, Tran N-T, Cheung N-M (2021) Infomax-gan: Improved adversarial image generation via information maximization and contrastive learning. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 3942\u20133952","DOI":"10.1109\/WACV48630.2021.00399"},{"key":"5522_CR25","doi-asserted-by":"crossref","unstructured":"Koh JY, Baldridge J, Lee H, Yang Y (2021) Text-to-image generation grounded by fine-grained user attention. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 237\u2013246","DOI":"10.1109\/WACV48630.2021.00028"},{"key":"5522_CR26","doi-asserted-by":"crossref","unstructured":"Gupta S, Keshari A, Das S (2022) Rv-gan: Recurrent gan for unconditional video generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2024\u20132033","DOI":"10.1109\/CVPRW56347.2022.00220"},{"key":"5522_CR27","unstructured":"Villegas R, Babaeizadeh M, Kindermans P-J, Moraldo H, Zhang H, Saffar MT, Castro S, Kunze J, Erhan D (2022) Phenaki: Variable length video generation from open domain textual description. arXiv preprint arXiv:2210.02399"},{"key":"5522_CR28","doi-asserted-by":"crossref","unstructured":"Wang Y, Bilinski P, Bremond F, Dantcheva A (2020) Imaginator: Conditional spatio-temporal gan for video generation. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1160\u20131169","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"5522_CR29","first-page":"165","volume":"43","author":"J Xiao","year":"2020","unstructured":"Xiao J, Shen M, Lei J, Xiong W, Jiao C (2020) Image conversion algorithm of haze scene based on generative adversarial networks. J Comput Sci 43:165\u2013176","journal-title":"J Comput Sci"},{"key":"5522_CR30","doi-asserted-by":"crossref","unstructured":"Torbunov D, Huang Y, Yu H, Huang J, Yoo S, Lin M, Viren B, Ren Y (2023) Uvcgan: Unet vision transformer cycle-consistent gan for unpaired image-to-image translation. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 702\u2013712","DOI":"10.1109\/WACV56688.2023.00077"},{"key":"5522_CR31","unstructured":"Zhang H, Zhou L, Wang R, Knoll A (2023) Attention mechanism for contrastive learning in gan-based image-to-image translation. arXiv preprint arXiv:2302.12052"},{"key":"5522_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106786","volume":"98","author":"B Liu","year":"2021","unstructured":"Liu B, Gan J, Wen B, LiuFu Y, Gao W (2021) An automatic coloring method for ethnic costume sketches based on generative adversarial networks. Appl Soft Comput 98:106786","journal-title":"Appl Soft Comput"},{"key":"5522_CR33","doi-asserted-by":"crossref","unstructured":"Afifi M, Brubaker MA, Brown MS (2021) Histogan: Controlling colors of gan-generated and real images via color histograms. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7941\u20137950","DOI":"10.1109\/CVPR46437.2021.00785"},{"key":"5522_CR34","doi-asserted-by":"publisher","unstructured":"Megahed M, Mohammed A (2023) A comprehensive review of generative adversarial networks: Fundamentals, applications, and challenges. WIREs Computational Statistics e1629 1\u201333. https:\/\/doi.org\/10.1002\/wics.1629","DOI":"10.1002\/wics.1629"},{"key":"5522_CR35","unstructured":"Almahairi A, Rajeshwar S, Sordoni A, Bachman P, Courville A (2018) Augmented cyclegan: Learning many-to-many mappings from unpaired data. In: International conference on machine learning, pp 195\u2013204 . PMLR"},{"key":"5522_CR36","unstructured":"Liu M-Y, Breuel T, Kautz J (2017) Unsupervised image-to-image translation networks. Adv Neural Inf Process Syst 700\u2013708"},{"key":"5522_CR37","doi-asserted-by":"crossref","unstructured":"Huang X, Liu M-Y, Belongie S, Kautz J (2018) Multimodal unsupervised image-to-image translation. In: Proceedings of the european conference on computer vision (ECCV), pp 172\u2013189","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"5522_CR38","unstructured":"Liu Y, De Nadai M, Yao J, Sebe N, Lepri B, Alameda-Pineda X (2020) Gmm-unit: Unsupervised multi-domain and multi-modal image-to-image translation via attribute gaussian mixture modeling. arXiv preprint arXiv:2003.06788"},{"key":"5522_CR39","doi-asserted-by":"crossref","unstructured":"Richardson E, Alaluf Y, Patashnik O, Nitzan Y, Azar Y, Shapiro S, Cohen-Or D (2021) Encoding in style: a stylegan encoder for image-to-image translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2287\u20132296","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"5522_CR40","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":"5522_CR41","doi-asserted-by":"crossref","unstructured":"Zhang P, Zhang B, Chen D, Yuan L, Wen F (2020) Cross-domain correspondence learning for exemplar-based image translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5143\u20135153","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"5522_CR42","doi-asserted-by":"publisher","unstructured":"Yang X, Wang Z, Wei Z, Yang D (2023) Scsp: An unsupervised image-to-image translation network based on semantic cooperative shape perception. IEEE Trans Multimed 1\u201311. https:\/\/doi.org\/10.1109\/TMM.2023.3328176","DOI":"10.1109\/TMM.2023.3328176"},{"issue":"3","key":"5522_CR43","doi-asserted-by":"publisher","first-page":"3144","DOI":"10.1109\/TII.2022.3160705","volume":"19","author":"X Zhang","year":"2023","unstructured":"Zhang X, Fan C, Xiao Z, Zhao L, Chen H, Chang X (2023) Random reconstructed unpaired image-to-image translation. IEEE Trans Ind Inform 19(3):3144\u20133154. https:\/\/doi.org\/10.1109\/TII.2022.3160705","journal-title":"IEEE Trans Ind Inform"},{"key":"5522_CR44","doi-asserted-by":"crossref","unstructured":"Lai X, Bai X, Hao Y (2021) Unsupervised generative adversarial networks with cross-model weight transfer mechanism for image-to-image translation. In: Proceedings of the IEEE\/CVF international conference on computer vision workshop, pp 1814\u20131822","DOI":"10.1109\/ICCVW54120.2021.00208"},{"key":"5522_CR45","doi-asserted-by":"crossref","unstructured":"Yuan S, Liu R, Chen M, Chen B, Qiu Z, He X (2022) Se-gan: Skeleton enhanced gan-based model for brush handwriting font generation. In: 2022 IEEE International conference on multimedia and expo (ICME), pp 1\u20136. IEEE","DOI":"10.1109\/ICME52920.2022.9859964"},{"key":"5522_CR46","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/j.neucom.2022.07.084","volume":"506","author":"J Zhao","year":"2022","unstructured":"Zhao J, Lee F, Hu C, Yu H, Chen Q (2022) Lda-gan: Lightweight domain-attention gan for unpaired image-to-image translation. Neurocomputing 506:355\u2013368","journal-title":"Neurocomputing"},{"key":"5522_CR47","doi-asserted-by":"crossref","unstructured":"Tang H, Xu D, Sebe N, Yan Y (2019) Attention-guided generative adversarial networks for unsupervised image-to-image translation. In: 2019 International joint conference on neural networks (IJCNN), pp 1\u20138. IEEE","DOI":"10.1109\/IJCNN.2019.8851881"},{"key":"5522_CR48","doi-asserted-by":"publisher","first-page":"110522","DOI":"10.1109\/ACCESS.2023.3322146","volume":"11","author":"H-T Choi","year":"2023","unstructured":"Choi H-T, Sohn B-S, Hong B-W (2023) Unsupervised image to image translation with additional mask. IEEE Access 11:110522\u2013110529. https:\/\/doi.org\/10.1109\/ACCESS.2023.3322146","journal-title":"IEEE Access"},{"issue":"12","key":"5522_CR49","doi-asserted-by":"publisher","first-page":"14777","DOI":"10.1109\/TPAMI.2023.3308102","volume":"45","author":"Y Dalva","year":"2023","unstructured":"Dalva Y, Pehlivan H, Hatipoglu OI, Moran C, Dundar A (2023) Image-to-image translation with disentangled latent vectors for face editing. IEEE Trans Pattern Anal Mach Intell 45(12):14777\u201314788. https:\/\/doi.org\/10.1109\/TPAMI.2023.3308102","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5522_CR50","doi-asserted-by":"crossref","unstructured":"Mao X, Li Q, Xie H, Lau RY, Wang Z, Paul Smolley S (2017) Least squares generative adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2794\u20132802","DOI":"10.1109\/ICCV.2017.304"},{"key":"5522_CR51","doi-asserted-by":"crossref","unstructured":"Hu X, Zhou X, Huang Q, Shi Z, Sun L, Li Q (2022) Qs-attn: Query-selected attention for contrastive learning in i2i translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 18291\u201318300","DOI":"10.1109\/CVPR52688.2022.01775"},{"key":"5522_CR52","doi-asserted-by":"crossref","unstructured":"Torbunov D, Huang Y, Yu H, Huang J, Yoo S, Lin M, Viren B, Ren Y (2023) Uvcgan: Unet vision transformer cycle-consistent gan for unpaired image-to-image translation. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 702\u2013712","DOI":"10.1109\/WACV56688.2023.00077"},{"key":"5522_CR53","doi-asserted-by":"crossref","unstructured":"Chen R, Huang W, Huang B, Sun F, Fang B (2020) Reusing discriminators for encoding: Towards unsupervised image-to-image translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8168\u20138177","DOI":"10.1109\/CVPR42600.2020.00819"},{"key":"5522_CR54","doi-asserted-by":"crossref","unstructured":"Xie S, Gong M, Xu Y, Zhang K (2021) Unaligned image-to-image translation by learning to reweight. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 14174\u201314184","DOI":"10.1109\/ICCV48922.2021.01391"},{"key":"5522_CR55","doi-asserted-by":"crossref","unstructured":"Lee H-Y, Tseng H-Y, Huang J-B, Singh M, Yang M-H (2018) Diverse image-to-image translation via disentangled representations. In: Proceedings of the european conference on computer vision (ECCV), pp 35\u201351","DOI":"10.1007\/978-3-030-01246-5_3"},{"key":"5522_CR56","unstructured":"Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv Neural Inf Process Syst 6629\u20136640"},{"key":"5522_CR57","unstructured":"Bi\u0144kowski M, Sutherland DJ, Arbel M, Gretton A (2018) Demystifying mmd gans. arXiv preprint arXiv:1801.01401"},{"key":"5522_CR58","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"5522_CR59","doi-asserted-by":"crossref","unstructured":"Yang L, Zhang Z, Song Y, Hong S, Xu R, Zhao Y, Zhang W, Cui B, Yang M-H (2023) Diffusion models: A comprehensive survey of methods and applications. ACM Comput Surv 56(4) Article No.105, pp 1\u201339","DOI":"10.1145\/3626235"},{"key":"5522_CR60","doi-asserted-by":"crossref","unstructured":"Huang R, Ren Y, Jiang Z, Cui C, Liu J, Zhao Z (2023) FastDiff 2: Revisiting and incorporating GANs and diffusion models in high-fidelity speech synthesis. In: Rogers A, Boyd-Graber J, Okazaki N (eds) Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics, Toronto, Canada, pp 6994\u20137009","DOI":"10.18653\/v1\/2023.findings-acl.437"},{"key":"5522_CR61","unstructured":"Zhang T, Wang Z, Huang J, Tasnim MM, Shi W (2023) A survey of diffusion based image generation models: Issues and their solutions. arXiv preprint arXiv:2308.13142"},{"key":"5522_CR62","doi-asserted-by":"crossref","unstructured":"Berrada T, Verbeek J, Couprie C, Alahari K (2024) Unlocking pre-trained image backbones for semantic image synthesis. arXiv preprint arXiv:2312.13314","DOI":"10.1109\/CVPR52733.2024.00749"},{"key":"5522_CR63","doi-asserted-by":"publisher","unstructured":"Pan X, Tewari A, Leimk\u00fchler T, Liu L, Meka A, Theobalt C (2023) Drag your gan: Interactive point-based manipulation on the generative image manifold. In: ACM SIGGRAPH 2023 conference proceedings. SIGGRAPH \u201923. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3588432.3591500","DOI":"10.1145\/3588432.3591500"},{"key":"5522_CR64","doi-asserted-by":"publisher","unstructured":"Kang M, Zhu J-Y, Zhang R, Park J, Shechtman E, Paris S, Park T (2023) Scaling up gans for text-to-image synthesis. In: 2023 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 10124\u201310134. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00976","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"5522_CR65","unstructured":"Wang Z, Zheng H, He P, Chen W, Zhou M (2023) Diffusion-gan: Training gans with diffusion. In: Proceedings of international conference on learning representations, pp 1\u201326"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05522-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05522-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05522-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T11:12:05Z","timestamp":1732014725000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05522-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":65,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["5522"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05522-x","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]},"assertion":[{"value":"10 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2024","order":2,"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 the datasets used in this study are publicly available and that there are no ethical issues related to this study, as it does not involve humans or animals.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data use"}},{"value":"The authors declare no conflicts of interest and no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests\/Conflicts of interest"}}]}}