{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T19:04:16Z","timestamp":1763665456488},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T00:00:00Z","timestamp":1714435200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T00:00:00Z","timestamp":1714435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s00371-024-03404-4","type":"journal-article","created":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:02:54Z","timestamp":1714521774000},"page":"3971-3984","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Attention mechanism-based generative adversarial networks for image cartoonization"],"prefix":"10.1007","volume":"40","author":[{"given":"Wenqing","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianlin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junwei","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,30]]},"reference":[{"key":"3404_CR1","volume-title":"Image and Video-Based Artistic Stylisation","author":"P Rosin","year":"2012","unstructured":"Rosin, P., Collomosse, J.: Image and Video-Based Artistic Stylisation, 2nd edn. Springer, Berlin (2012)","edition":"2"},{"key":"3404_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, pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"3404_CR3","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"3404_CR4","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, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"3404_CR5","doi-asserted-by":"publisher","unstructured":"Chen, Y., Lai, Y.-K., Liu, Y.-J.: CartoonGAN: generative adversarial networks for photo cartoonization. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9465\u20139474. Salt Lake City, UT, USA. https:\/\/doi.org\/10.1109\/CVPR.2018.00986 (2018)","DOI":"10.1109\/CVPR.2018.00986"},{"key":"3404_CR6","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: Attention-aware multi-stroke style transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00156"},{"key":"3404_CR7","doi-asserted-by":"crossref","unstructured":"Park, D.Y., Lee, K.H.: Arbitrary style transfer with style-attentional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00603"},{"key":"3404_CR8","doi-asserted-by":"crossref","unstructured":"Woo, S., et al.: Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"3404_CR9","unstructured":"Larochelle, H., Hinton, G.E.: Learning to combine foveal glimpses with a third-order Boltzmann machine. In: Advances in Neural Information Processing Systems, vol. 23 (2010)"},{"key":"3404_CR10","unstructured":"Mnih, V., Heess, N., Graves, A.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, vol. 27 (2010)"},{"key":"3404_CR11","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., et al.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"3404_CR12","doi-asserted-by":"crossref","unstructured":"Carion, N., et al.: End-to-end object detection with transformers. In: European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3404_CR13","unstructured":"Guan, Q., et al.: Diagnose like a radiologist: attention guided convolutional neural network for thorax disease classification. arXiv:1801.09927 (2018)"},{"key":"3404_CR14","unstructured":"Zhang, H., et al.: Self-attention generative adversarial networks. In: International Conference on Machine Learning. PMLR (2019)"},{"key":"3404_CR15","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"F Author","year":"2023","unstructured":"Author, F.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2023)","journal-title":"IEEE Trans. Multimedia"},{"issue":"10","key":"3404_CR16","doi-asserted-by":"publisher","first-page":"7719","DOI":"10.1109\/TNNLS.2022.3146004","volume":"34","author":"F Author","year":"2023","unstructured":"Author, F.: FSAD-Net: feedback spatial attention dehazing network. IEEE Trans. Neural Netw. Learn. Syst. 34(10), 7719\u20137733 (2023)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3404_CR17","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Hierarchical pyramid diverse attention networks for face recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00835"},{"key":"3404_CR18","doi-asserted-by":"crossref","unstructured":"Chen, B., Deng, W., Hu, J.: Mixed high-order attention network for person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00046"},{"key":"3404_CR19","doi-asserted-by":"crossref","unstructured":"Wang, F., et al.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.683"},{"issue":"8","key":"3404_CR20","doi-asserted-by":"publisher","first-page":"3597","DOI":"10.1007\/s00371-023-02922-x","volume":"39","author":"Yiming Qin","year":"2023","unstructured":"Qin, Yiming, et al.: GuideRender: large-scale scene navigation based on multi-modal view frustum movement prediction. Visual Comput. 39(8), 3597\u20133607 (2023)","journal-title":"Visual Comput."},{"key":"3404_CR21","doi-asserted-by":"crossref","unstructured":"Xu, L., Lu, C., Xu, Y., et al. Image smoothing via L0 gradient minimization. In: Proceedings of the 2011 SIGGRAPH Asia Conference, pp. 1\u201312 (2011)","DOI":"10.1145\/2070781.2024208"},{"key":"3404_CR22","doi-asserted-by":"crossref","unstructured":"Gatys, L., Ecker, A.S., Bethge, M.: Texture synthesis using convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)","DOI":"10.1109\/CVPR.2016.265"},{"key":"3404_CR23","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1109\/TIP.2021.3136619","volume":"31","author":"Anam Nazir","year":"2021","unstructured":"Nazir, Anam, et al.: Ecsu-net: an embedded clustering sliced u-net coupled with fusing strategy for efficient intervertebral disc segmentation and classification. IEEE Trans. Image Process. 31, 880\u2013893 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"3404_CR24","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TNNLS.2022.3175775","volume":"35","author":"A Karambakhsh","year":"2022","unstructured":"Karambakhsh, A., et al.: SparseVoxNet: 3-D object recognition with sparsely aggregation of 3-D dense blocks. IEEE Trans. Neural Netw. Learn. Syst. 35, 532\u2013546 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3404_CR25","doi-asserted-by":"crossref","unstructured":"Li, C., Wand, M.: Combining Markov random fields and convolutional neural networks for image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2479\u20132486 (2016)","DOI":"10.1109\/CVPR.2016.272"},{"key":"3404_CR26","doi-asserted-by":"crossref","unstructured":"Chen, Y., Lai, Y.K., Liu, Y.J.: Transforming photos to comics using convolutional neural networks. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 2010\u20132014 (2017)","DOI":"10.1109\/ICIP.2017.8296634"},{"key":"3404_CR27","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J. Y., Zhou, T., et al.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"3404_CR28","doi-asserted-by":"crossref","unstructured":"Huang, X., Liu, M. Y., Belongie, S., et al.: Multimodal unsupervised image-to-image translation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 172\u2013189 (2018)","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"3404_CR29","doi-asserted-by":"crossref","unstructured":"Lee, H.Y., Tseng, H.Y., Huang, J.B., et al.: Diverse image-to-image translation via disentangled representations. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 35\u201351 (2018)","DOI":"10.1007\/978-3-030-01246-5_3"},{"issue":"6","key":"3404_CR30","first-page":"2330","volume":"32","author":"Y Sin","year":"2020","unstructured":"Sin, Y., et al.: Broad colorization. IEEE Trans. Neural Netw. Learn. Syst. 32(6), 2330\u20132343 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"6","key":"3404_CR31","first-page":"1","volume":"37","author":"L Zhang","year":"2018","unstructured":"Zhang, L., Li, C., Wong, T.T., et al.: Two-stage sketch colorization. ACM Trans. Graph. (TOG) 37(6), 1\u201314 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"10","key":"3404_CR32","doi-asserted-by":"publisher","first-page":"5346","DOI":"10.1109\/TNNLS.2021.3070463","volume":"33","author":"P Li","year":"2021","unstructured":"Li, P., Sheng, B., Philip Chen, C.L.: Face sketch synthesis using regularized broad learning system. IEEE Trans. Neural Netw. Learn. Syst. 33(10), 5346\u20135360 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3404_CR33","doi-asserted-by":"publisher","first-page":"8526","DOI":"10.1109\/TIP.2021.3117061","volume":"30","author":"H Li","year":"2021","unstructured":"Li, H., Sheng, B., Li, P., et al.: Globally and locally semantic colorization via exemplar-based broad-GAN. IEEE Trans. Image Process. 30, 8526\u20138539 (2021)","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"3404_CR34","doi-asserted-by":"publisher","first-page":"3647","DOI":"10.1007\/s00371-023-02938-3","volume":"39","author":"Shan Huang","year":"2023","unstructured":"Huang, Shan, et al.: TransMRSR: transformer-based self-distilled generative prior for brain MRI super-resolution. Visual Comput. 39(8), 3647\u20133659 (2023)","journal-title":"Visual Comput."},{"issue":"5","key":"3404_CR35","doi-asserted-by":"publisher","first-page":"2735","DOI":"10.1109\/TCYB.2019.2934823","volume":"51","author":"H Guo","year":"2021","unstructured":"Guo, H., Sheng, B., Li, P., Chen, C.P.: Multiview high dynamic range image synthesis using fuzzy broad learning system. IEEE Trans. Cybern. 51(5), 2735\u20132747 (2021)","journal-title":"IEEE Trans. Cybern."},{"key":"3404_CR36","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Yang, Q., Sheng, B.: Deep colorization. In: Proceedings of the IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.55"},{"key":"3404_CR37","unstructured":"Dumoulin, V., Belghazi, I., Poole, B., Lamb, A., Arjovsky, M., Mastropietro, O., Courville, A.C.: Adversarially Learned Inference. arXiv:1606.00704 (2016)"},{"key":"3404_CR38","unstructured":"Karacan, L., Akata, Z., Erdem, A., Erdem, E.: Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts. arXiv:1612.00215 (2016)"},{"key":"3404_CR39","unstructured":"Liu, M.Y., Breuel,T., Kautz, J.: Unsupervised image-to-image translation networks. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"3404_CR40","doi-asserted-by":"crossref","unstructured":"Cho, W., et al.: Image-to-image translation via group-wise deep whitening-and-coloring transformation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.01089"},{"issue":"10","key":"3404_CR41","doi-asserted-by":"publisher","first-page":"3376","DOI":"10.1109\/TVCG.2021.3067201","volume":"28","author":"Y Shu","year":"2021","unstructured":"Shu, Y., et al.: Gan-based multi-style photo cartoonization. IEEE Trans. Vis. Comput. Graph. 28(10), 3376\u20133390 (2021)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"3404_CR42","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, J.: Learning to Cartoonize using white-box cartoon representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00811"},{"key":"3404_CR43","unstructured":"Heusel, M., et al.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03404-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03404-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03404-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T11:24:29Z","timestamp":1717673069000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03404-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,30]]},"references-count":43,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["3404"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03404-4","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,30]]},"assertion":[{"value":"3 April 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}