{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T11:52:28Z","timestamp":1783597948100,"version":"3.55.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T00:00:00Z","timestamp":1734480000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T00:00:00Z","timestamp":1734480000000},"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":"crossref","award":["No. 62172003"],"award-info":[{"award-number":["No. 62172003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11227-024-06787-2","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T15:00:52Z","timestamp":1734534052000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["LVAST: a lightweight vision transformer for effective arbitrary style transfer"],"prefix":"10.1007","volume":"81","author":[{"given":"Gaoming","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenlong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiujun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianjin","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,18]]},"reference":[{"key":"6787_CR1","doi-asserted-by":"publisher","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 (CVPR), 2414\u20132423 https:\/\/doi.org\/10.1109\/CVPR.2016.265","DOI":"10.1109\/CVPR.2016.265"},{"key":"6787_CR2","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II","author":"J Johnson","year":"2016","unstructured":"Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer Vision \u2013 ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II. Springer International Publishing, Cham, pp 694\u2013711. https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"issue":"11","key":"6787_CR3","doi-asserted-by":"publisher","first-page":"3365","DOI":"10.1109\/TVCG.2019.2921336","volume":"26","author":"Y Jing","year":"2020","unstructured":"Jing Y, Yang Y, Feng Z, Ye J, Yu Y, Song M (2020) Neural style transfer: a review. IEEE Trans Visual Comput Graphics 26(11):3365\u20133385. https:\/\/doi.org\/10.1109\/TVCG.2019.2921336","journal-title":"IEEE Trans Visual Comput Graphics"},{"key":"6787_CR4","doi-asserted-by":"publisher","unstructured":"Ulyanov D, Vedaldi A, Lempitsky V (2017) Improved texture networks: maximizing quality and diversity in feed-forward stylization and texture synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6924\u20136932 https:\/\/doi.org\/10.1109\/CVPR.2017.437","DOI":"10.1109\/CVPR.2017.437"},{"key":"6787_CR5","doi-asserted-by":"publisher","unstructured":"Kotovenko D, Sanakoyeu A, Lang S, Ommer B (2019) Content and style disentanglement for artistic style transfer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 4422\u20134431https:\/\/doi.org\/10.1109\/ICCV.2019.00452","DOI":"10.1109\/ICCV.2019.00452"},{"key":"6787_CR6","doi-asserted-by":"publisher","unstructured":"Li Y, Fang C, Yang J, Wang Z, Lu X, Yang MH (2017) Diversified texture synthesis with feed-forward networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3920-3928 https:\/\/doi.org\/10.1109\/CVPR.2017.36","DOI":"10.1109\/CVPR.2017.36"},{"key":"6787_CR7","doi-asserted-by":"publisher","first-page":"2373","DOI":"10.1109\/TPAMI.2020.2964205","volume":"43","author":"D Chen","year":"2021","unstructured":"Chen D, Yuan L, Liao J, Yu N, Hua G (2021) Explicit filterbank learning for neural image style transfer and image processing. IEEE Trans Pattern Anal Mach Intell 43:2373\u20132387. https:\/\/doi.org\/10.1109\/TPAMI.2020.2964205","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6787_CR8","doi-asserted-by":"publisher","unstructured":"Huang X, Belongie S (2017) Arbitrary style transfer in real-time with adaptive instance normalization. In: 2017 IEEE International Conference on Computer Vision (ICCV), 1510\u20131519 https:\/\/doi.org\/10.1109\/ICCV.2017.167","DOI":"10.1109\/ICCV.2017.167"},{"key":"6787_CR9","first-page":"386","volume":"30","author":"Y Li","year":"2017","unstructured":"Li Y, Fang C, Yang J, Wang Z, Lu X, Yang MH (2017) Universal style transfer via feature transforms. Adv Neural Inf Process Syst 30:386\u2013396","journal-title":"Adv Neural Inf Process Syst"},{"key":"6787_CR10","doi-asserted-by":"publisher","unstructured":"Li X, Liu S, Kautz J, Yang MH 2019 Learning linear transformations for fast image and video style transfer. In: the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3809\u20133817 https:\/\/doi.org\/10.1109\/CVPR.2019.00393","DOI":"10.1109\/CVPR.2019.00393"},{"key":"6787_CR11","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations"},{"key":"6787_CR12","doi-asserted-by":"publisher","unstructured":"Park DY, Lee KH (2019) Arbitrary style transfer with style-attentional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5873\u20135881 https:\/\/doi.org\/10.1109\/CVPR.2019.00603","DOI":"10.1109\/CVPR.2019.00603"},{"key":"6787_CR13","doi-asserted-by":"publisher","unstructured":"Deng Y, Tang F, Dong W, Ma C, Pan X, Wang L, Xu C (2022) StyTr2: image style transfer with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 11326\u201311336 https:\/\/doi.org\/10.1109\/CVPR52688.2022.01104","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"6787_CR14","doi-asserted-by":"publisher","unstructured":"Zhang C, Yang J, Wang L, Dai Z (2024) S2WAT: Image style transfer via hierarchical vision transformer using strips window attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, 7024\u20137032 https:\/\/doi.org\/10.1609\/aaai.v38i7.28529","DOI":"10.1609\/aaai.v38i7.28529"},{"key":"6787_CR15","unstructured":"Chen H, Zhao L, Wang Z, Zhang H, Zuo Z, Li A, Xing W, Lu D (2021) Artistic style transfer with internal-external learning and contrastive learning. In: advances in Neural Information Processing Systems, pp. 26561\u201326573"},{"key":"6787_CR16","doi-asserted-by":"publisher","unstructured":"An J, Huang S, Song Y, Dou D, Liu W, Luo J (2021) ArtFlow: unbiased image style transfer via reversible neural flows. In: proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 862\u2013871. https:\/\/doi.org\/10.1109\/CVPR46437.2021","DOI":"10.1109\/CVPR46437.2021"},{"key":"6787_CR17","doi-asserted-by":"publisher","unstructured":"Wu Z, Zhu Z, Du J, Bai X (2022) CCPL: contrastive coherence preserving loss for versatile style transfer. In: The European Conference on Computer Vision (ECCV). Computer Vision \u2013 ECCV, 189\u2013206 https:\/\/doi.org\/10.1007\/978-3-031-19787-1_11","DOI":"10.1007\/978-3-031-19787-1_11"},{"key":"6787_CR18","doi-asserted-by":"publisher","unstructured":"Wang Z, Zhang Z, Zhao L, Zuo Z, Li A, Xing W, Lu D (2022) AesUST: Towards aesthetic-enhanced universal style transfer. In: Proceedings of the 30th ACM International Conference on Multimedia, 1095\u20131106 https:\/\/doi.org\/10.1109\/10.1145\/3503161.3547939","DOI":"10.1109\/10.1145\/3503161.3547939"},{"issue":"3","key":"6787_CR19","doi-asserted-by":"publisher","first-page":"2742","DOI":"10.1609\/aaai.v37i3.25374","volume":"37","author":"Z Wang","year":"2023","unstructured":"Wang Z, Zhao L, Zuo Z, Li A, Chen H, Xing W, Dongming L (2023) MicroAST: towards super-fast ultra-resolution arbitrary style transfer. Proc AAAI Conf Artif Intell 37(3):2742\u20132750. https:\/\/doi.org\/10.1609\/aaai.v37i3.25374","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"6787_CR20","doi-asserted-by":"crossref","unstructured":"Chen H, Zhao L, Li J, Yang J (2023) Tssat: two-stage statistics-aware transformation for artistic style transfer. In: proceedings of the 31st ACM International Conference on Multimedia, 6878\u20136887","DOI":"10.1145\/3581783.3611819"},{"issue":"12","key":"6787_CR21","doi-asserted-by":"publisher","first-page":"13310","DOI":"10.1609\/aaai.v38i12.29232","volume":"38","author":"J Kwon","year":"2024","unstructured":"Kwon J, Kim S, Lin Y, Yoo S, Cha J (2024) Aesfa: an aesthetic feature-aware arbitrary neural style transfer. Proc AAAI Conf Artif Intell 38(12):13310\u201313319. https:\/\/doi.org\/10.1609\/aaai.v38i12.29232","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"6787_CR22","doi-asserted-by":"publisher","unstructured":"Deng Y, Tang F, Dong W, Sun W, Huang F, Xu C (2020) Arbitrary style transfer via multi-adaptation network. In: Proceedings of the 28th ACM International Conference on Multimedia, 2719\u20132727 https:\/\/doi.org\/10.1145\/3394171.3414015","DOI":"10.1145\/3394171.3414015"},{"key":"6787_CR23","doi-asserted-by":"publisher","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 10012\u201310022. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"6787_CR24","unstructured":"Mehta S, Rastegari M (2023) separable self-attention for mobile vision transformers. In: transactions on Machine Learning Research"},{"key":"6787_CR25","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: transformers for image recognition at scale. In: international Conference on Learning Representations"},{"key":"6787_CR26","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1109\/TIP.2022.3229614","volume":"32","author":"W Yu","year":"2023","unstructured":"Yu W, Zhu M, Wang N, Wang X, Gao X (2023) An efficient transformer based on global and local self-attention for face photo-sketch synthesis. IEEE Trans Image Process 32:483\u2013495. https:\/\/doi.org\/10.1109\/TIP.2022.3229614","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"6787_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3550454.3555471","volume":"41","author":"Z Huang","year":"2022","unstructured":"Huang Z, Zhao N, Liao J (2022) UniColor: a unified framework for multi-modal colorization with transformer. ACM Trans Graph 41(6):1\u201316. https:\/\/doi.org\/10.1145\/3550454.3555471","journal-title":"ACM Trans Graph"},{"key":"6787_CR28","doi-asserted-by":"publisher","unstructured":"Dai Z, Cai B, Lin Y, Chen J (2021) UP-DETR: unsupervised pre-training for object detection with transformers. In: proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 1601\u20131610. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00165","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"6787_CR29","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.neucom.2023.03.031","volume":"535","author":"Z Cao","year":"2023","unstructured":"Cao Z, Zhang J (2023) Gradient-coupled cross-patch attention map for weakly supervised semantic segmentation. Neurocomputing 535:83\u201396. https:\/\/doi.org\/10.1016\/j.neucom.2023.03.031","journal-title":"Neurocomputing"},{"key":"6787_CR30","unstructured":"Mehta S, Rastegari M (2022) MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. In: international Conference on Learning Representations"},{"key":"6787_CR31","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: proceedings of the International Conference on Machine Learning, 1597\u20131607. PMLR"},{"key":"6787_CR32","doi-asserted-by":"publisher","unstructured":"Chen X, He K (2021) Exploring simple siamese representation learning. In: proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 15750\u201315758. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01549","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"6787_CR33","doi-asserted-by":"publisher","first-page":"6761","DOI":"10.1109\/TIP.2022.3215899","volume":"31","author":"X Wang","year":"2022","unstructured":"Wang X, Wang W, Yang S, Liu J (2022) CLAST: contrastive learning for arbitrary style transfer. IEEE Trans Image Process 31:6761\u20136772. https:\/\/doi.org\/10.1109\/TIP.2022.3215899","journal-title":"IEEE Trans Image Process"},{"key":"6787_CR34","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.neunet.2023.04.037","volume":"164","author":"Y Zhang","year":"2023","unstructured":"Zhang Y, Tian Y, Hou J (2023) CSAST: content self-supervised and style contrastive learning for arbitrary style transfer. Neural Netw 164:146\u2013155. https:\/\/doi.org\/10.1016\/j.neunet.2023.04.037","journal-title":"Neural Netw"},{"key":"6787_CR35","doi-asserted-by":"publisher","first-page":"1369","DOI":"10.1007\/s00371-023-02855-5","volume":"40","author":"X Yu","year":"2023","unstructured":"Yu X, Zhou G (2023) Arbitrary style transfer via content consistency and style consistency. Vis Comput 40:1369\u20131382. https:\/\/doi.org\/10.1007\/s00371-023-02855-5","journal-title":"Vis Comput"},{"key":"6787_CR36","unstructured":"Yu T, Zhao G, Li P, Yu Y (2022) BOAT: bilateral local attention vision transformer. In: 33rd British Machine Vision Conference"},{"key":"6787_CR37","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V","author":"T-Y Lin","year":"2014","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Piotr Doll\u00e1r C, Zitnick L (2014) Microsoft COCO: common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer Vision \u2013 ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V. Springer International Publishing, Cham, pp 740\u2013755. https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"3","key":"6787_CR38","doi-asserted-by":"publisher","first-page":"593","DOI":"10.2308\/iace-50038","volume":"26","author":"F Phillips","year":"2011","unstructured":"Phillips F, Mackintosh B (2011) Wiki art gallery, inc.: a case for critical thinking. Issues in Acc Edu 26(3):593\u2013608. https:\/\/doi.org\/10.2308\/iace-50038","journal-title":"Issues in Acc Edu"},{"key":"6787_CR39","unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: international Conference on Learning Representations"},{"key":"6787_CR40","unstructured":"Xiong R, Yang Y, He D, Zheng K, Zheng S, Xing C, Zhang H, Lan Y, Wang L, Liu T (2020) On layer normalization in the transformer architecture. In: proceedings of the International Conference on Machine Learning, pp. 10524\u201310533. PMLR"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06787-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06787-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06787-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T15:07:43Z","timestamp":1734534463000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06787-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,18]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6787"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06787-2","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,18]]},"assertion":[{"value":"27 November 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"305"}}