{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T09:45:47Z","timestamp":1758361547673,"version":"3.44.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T00:00:00Z","timestamp":1740355200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T00:00:00Z","timestamp":1740355200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100012542","name":"Sichuan Province Science and Technology Support Program","doi-asserted-by":"publisher","award":["2024NSFSC0499"],"award-info":[{"award-number":["2024NSFSC0499"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s10489-025-06384-7","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T07:43:30Z","timestamp":1740383010000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DropMismatch: removing mismatched UI elements for better pixel to code generation"],"prefix":"10.1007","volume":"55","author":[{"given":"Ming","family":"Li","sequence":"first","affiliation":[]},{"given":"Tao","family":"Lin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,24]]},"reference":[{"key":"6384_CR1","unstructured":"Malik S, Saeed MT, Zia MJ, Rasool S, Khan LA, Ahmed MI (2023) Reimagining Application User Interface (UI) Design using Deep Learning Methods: Challenges and Opportunities. arXiv:2303.13055 Accessed 2023-08-28"},{"key":"6384_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cola.2023.101202","volume":"75","author":"T Kaluarachchi","year":"2023","unstructured":"Kaluarachchi T, Wickramasinghe M (2023) A systematic literature review on automatic website generation. J Comput Lang 75:101202. https:\/\/doi.org\/10.1016\/j.cola.2023.101202","journal-title":"J Comput Lang"},{"key":"6384_CR3","doi-asserted-by":"publisher","unstructured":"Beltramelli T (2018) Pix2code: Generating Code from a Graphical User Interface Screenshot. In: Proceedings of the ACM SIGCHI Symposium on engineering interactive computing systems. EICS. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3220134.3220135","DOI":"10.1145\/3220134.3220135"},{"key":"6384_CR4","doi-asserted-by":"crossref","unstructured":"Chen C, Su T, Meng G, Xing Z, Liu Y (2018) From UI Design Image to GUI Skeleton: A Neural Machine Translator to Bootstrap Mobile GUI Implementation. In: 2018 IEEE\/ACM 40th International conference on software engineering (ICSE), pp 665\u2013676","DOI":"10.1145\/3180155.3180240"},{"issue":"11","key":"6384_CR5","doi-asserted-by":"publisher","first-page":"8135","DOI":"10.1109\/TNNLS.2022.3152527","volume":"34","author":"H Song","year":"2022","unstructured":"Song H, Kim M, Park D, Shin Y, Lee J-G (2022) Learning from noisy labels with deep neural networks: A survey. IEEE Trans Neural Netw Learn Syst 34(11):8135\u20138153","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"6384_CR6","doi-asserted-by":"publisher","unstructured":"Deka B, Huang Z, Franzen C, Hibschman J, Afergan D, Li Y, Nichols J, Kumar R (2017) Rico: A Mobile App Dataset for Building Data-Driven Design Applications. In: Proceedings of the 30th annual ACM symposium on user interface software and technology. UIST, pp 845\u2013854. ACM, Qu\u00e9bec City QC Canada. https:\/\/doi.org\/10.1145\/3126594.3126651","DOI":"10.1145\/3126594.3126651"},{"key":"6384_CR7","doi-asserted-by":"publisher","unstructured":"Wu J, Wang S, Shen S, Peng Y-H, Nichols J, Bigham JP (2023) WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics. In: Proceedings of the 2023 CHI Conference on human factors in computing systems. CHI. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3544548.3581158","DOI":"10.1145\/3544548.3581158"},{"key":"6384_CR8","doi-asserted-by":"publisher","unstructured":"Li G, Baechler G, Tragut M, Li Y (2022) Learning to Denoise Raw Mobile UI Layouts for Improving Datasets at Scale. In: Proceedings of the 2022 CHI conference on human factors in computing systems. CHI. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3491102.3502042","DOI":"10.1145\/3491102.3502042"},{"key":"6384_CR9","doi-asserted-by":"crossref","unstructured":"Kang W, Mun J, Lee S, Roh B (2023) Noise-aware learning from web-crawled image-text data for image captioning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2942\u20132952","DOI":"10.1109\/ICCV51070.2023.00275"},{"key":"6384_CR10","doi-asserted-by":"crossref","unstructured":"Fu Z, Song K, Zhou L, Yang Y (2024) Noise-aware image captioning with progressively exploring mismatched words. In: Proceedings of the AAAI conference on artificial intelligence, vol. 38, pp 12091\u201312099","DOI":"10.1609\/aaai.v38i11.29097"},{"key":"6384_CR11","doi-asserted-by":"crossref","unstructured":"Nguyen TA, Csallner C (2015) Reverse Engineering Mobile Application User Interfaces With REMAUI. ASE","DOI":"10.1109\/ASE.2015.32"},{"issue":"2","key":"6384_CR12","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/TSE.2018.2844788","volume":"46","author":"K Moran","year":"2020","unstructured":"Moran K, Bernal-C\u00e1rdenas C, Curcio M, Bonett R, Poshyvanyk D (2020) Machine Learning-Based Prototyping of Graphical User Interfaces for Mobile Apps. IEEE Trans Softw Eng 46(2):196\u2013221. https:\/\/doi.org\/10.1109\/TSE.2018.2844788","journal-title":"IEEE Trans Softw Eng"},{"key":"6384_CR13","unstructured":"Baul\u00e9 D, Hauck JCR, J\u00fanior ECV (2025) Automatic code generation from sketches of mobile applications in end-user development using Deep Learning"},{"key":"6384_CR14","doi-asserted-by":"publisher","unstructured":"Wu J, Zhang X, Nichols J, Bigham JP (2021) Screen Parsing: Towards Reverse Engineering of UI Models from Screenshots. In: The 34th Annual ACM symposium on user interface software and technology. UIST, pp 470\u2013483. ACM, Virtual Event USA. https:\/\/doi.org\/10.1145\/3472749.3474763","DOI":"10.1145\/3472749.3474763"},{"key":"6384_CR15","doi-asserted-by":"publisher","unstructured":"Feng Z, Fang J, Cai B, Zhang Y (2021) GUIS2Code: A Computer Vision Tool to Generate Code Automatically from Graphical User Interface Sketches. In: Farka\u0161 I, Masulli P, Otte S, Wermter S (eds.) Artificial Neural Networks and Machine Learning \u2013 ICANN 2021. ICANN, pp 53\u201365. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-86365-4_5","DOI":"10.1007\/978-3-030-86365-4_5"},{"issue":"1","key":"6384_CR16","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1109\/TPAMI.2022.3148210","volume":"45","author":"M Stefanini","year":"2022","unstructured":"Stefanini M, Cornia M, Baraldi L, Cascianelli S, Fiameni G, Cucchiara R (2022) From show to tell: A survey on deep learning-based image captioning. IEEE Trans Pattern Anal Mach Intell 45(1):539\u2013559","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6384_CR17","doi-asserted-by":"crossref","unstructured":"Zhu Z, Xue Z, Yuan Z (2019) Automatic Graphics Program Generation Using Attention-Based Hierarchical Decoder. In: Jawahar CV, Li H, Mori G, Schindler K (eds.) Computer Vision \u2013 ACCV 2018. ACCV. Springer, Cham, pp 181\u2013196","DOI":"10.1007\/978-3-030-20876-9_12"},{"key":"6384_CR18","doi-asserted-by":"publisher","unstructured":"Pang X, Zhou Y, Li P, Lin W, Wu W, Wang JZ (2020) A novel syntax-aware automatic graphics code generation with attention-based deep neural network. J Netw Comput Appl 161:102636. https:\/\/doi.org\/10.1016\/j.jnca.2020.102636","DOI":"10.1016\/j.jnca.2020.102636"},{"issue":"1","key":"6384_CR19","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/s00530-021-00804-7","volume":"28","author":"W-Y Chen","year":"2022","unstructured":"Chen W-Y, Podstreleny P, Cheng W-H, Chen Y-Y, Hua K-L (2022) Code generation from a graphical user interface via attention-based encoder-decoder model. Multimed Syst 28(1):121\u2013130. https:\/\/doi.org\/10.1007\/s00530-021-00804-7","journal-title":"Multimed Syst"},{"key":"6384_CR20","doi-asserted-by":"publisher","unstructured":"Zhang W, Luan S, Tian L (2022) A Rapid Combined Model for Automatic Generating Web UI Codes. Wireless Commun Mobile Comput 2022:1\u201310. https:\/\/doi.org\/10.1155\/2022\/4415479","DOI":"10.1155\/2022\/4415479"},{"key":"6384_CR21","doi-asserted-by":"publisher","unstructured":"Zhang Z, Ding Y, Huang C (2023) Automatic Front-end Code Generation from image Via Multi-Head Attention. In: 2023 4th International conference on computer engineering and application (ICCEA). ICCEA, pp 869\u2013872. https:\/\/doi.org\/10.1109\/ICCEA58433.2023.10135462","DOI":"10.1109\/ICCEA58433.2023.10135462"},{"key":"6384_CR22","unstructured":"UXArchive - Made by Waldo. http:\/\/uxarchive.com\/ Accessed 2024-08-28"},{"key":"6384_CR23","unstructured":"UI Library designs, themes, templates and downloadable graphic elements on Dribbble. https:\/\/dribbble.com\/tags\/ui-library Accessed 2024-08-28"},{"key":"6384_CR24","doi-asserted-by":"publisher","unstructured":"Soui M, Haddad Z (2023) Deep Learning-Based Model Using DensNet201 for Mobile User Interface Evaluation. Int J Human\u2013Comput Interact 39(9):1981\u20131994. https:\/\/doi.org\/10.1080\/10447318.2023.2175494","DOI":"10.1080\/10447318.2023.2175494"},{"key":"6384_CR25","doi-asserted-by":"publisher","unstructured":"Sermuga\u00a0Pandian VP, Suleri S, Jarke M (2021) SynZ: Enhanced Synthetic Dataset for Training UI Element Detectors. In: 26th International conference on intelligent user interfaces. IUI. ACM, College Station TX USA, pp 67\u201369. https:\/\/doi.org\/10.1145\/3397482.3450725","DOI":"10.1145\/3397482.3450725"},{"key":"6384_CR26","doi-asserted-by":"crossref","unstructured":"Gu Z, Xu Z, Chen H, Lan J, Meng C, Wang W (2023) Mobile User Interface Element Detection via Adaptively Prompt Tuning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). CVPR, pp 11155\u201311164","DOI":"10.1109\/CVPR52729.2023.01073"},{"key":"6384_CR27","doi-asserted-by":"publisher","unstructured":"Chen C, Feng S, Xing Z, Liu L, Zhao S, Wang J (2019) Gallery D.C.: Design Search and Knowledge Discovery through Auto-created GUI Component Gallery. Proceed ACM on Human-Comput Interact 3(CSCW):1\u201322. https:\/\/doi.org\/10.1145\/3359282","DOI":"10.1145\/3359282"},{"key":"6384_CR28","unstructured":"Banerjee P, Mahajan S, Arora K, Baral C, Riva O (2023) Lexi: Self-Supervised Learning of the UI Language. arXiv:2301.10165 Accessed 2023-08-28"},{"key":"6384_CR29","doi-asserted-by":"publisher","unstructured":"Deka B, Huang Z, Kumar R (2016) ERICA: Interaction Mining Mobile Apps. In: Proceedings of the 29th annual symposium on user interface software and technology. UIST. ACM, Tokyo Japan, pp 767\u2013776. https:\/\/doi.org\/10.1145\/2984511.2984581","DOI":"10.1145\/2984511.2984581"},{"key":"6384_CR30","unstructured":"Write automated tests with UI Automator. https:\/\/developer.android.com\/training\/testing\/other-components\/ui-automator Accessed 2024-08-28"},{"key":"6384_CR31","doi-asserted-by":"publisher","unstructured":"Deka B, Doosti B, Huang F, Franzen C, Hibschman J, Afergan D, Li Y, Kumar R, Dong T, Nichols J (2021) An Early Rico Retrospective: Three Years of Uses for a Mobile App Dataset. In: Li Y, Hilliges O (eds.) Artificial Intelligence for Human Computer Interaction: A Modern Approach. Human\u2013Computer Interaction Series, Springer, Cham, pp 229\u2013256. https:\/\/doi.org\/10.1007\/978-3-030-82681-9_8","DOI":"10.1007\/978-3-030-82681-9_8"},{"key":"6384_CR32","doi-asserted-by":"publisher","unstructured":"Liu TF, Craft M, Situ J, Yumer E, Mech R, Kumar R (2018) Learning Design Semantics for Mobile Apps. In: Proceedings of the 31st Annual ACM symposium on user interface software and technology. UIST, ACM, Berlin Germany, pp 569\u2013579. https:\/\/doi.org\/10.1145\/3242587.3242650","DOI":"10.1145\/3242587.3242650"},{"key":"6384_CR33","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Doll\u00e1r P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1492\u20131500","DOI":"10.1109\/CVPR.2017.634"},{"key":"6384_CR34","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"6384_CR35","unstructured":"Morales-Brotons D, Vogels T, Hendrikx H (2024) Exponential moving average of weights in deep learning: Dynamics and benefits. Trans Mach Learn Res"},{"key":"6384_CR36","unstructured":"Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. arXiv:1711.05101"},{"key":"6384_CR37","unstructured":"Micikevicius P, Narang S, Alben J, Diamos G, Elsen E, Garcia D, Ginsburg B, Houston M, Kuchaiev O, Venkatesh G, et al (2017) Mixed precision training. arXiv:1710.03740"},{"key":"6384_CR38","doi-asserted-by":"crossref","unstructured":"M\u00fcller SG, Hutter F (2021) Trivialaugment: Tuning-free yet state-of-the-art data augmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 774\u2013782","DOI":"10.1109\/ICCV48922.2021.00081"},{"key":"6384_CR39","unstructured":"StratifiedGroupKFold. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.model_selection.StratifiedGroupKFold.html. Accessed 2024-08-26"},{"key":"6384_CR40","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Zemel R, Bengio Y (2015) Show, attend and tell: Neural image caption generation with visual attention. In: International conference on machine learning, PMLR, pp 2048\u20132057"},{"key":"6384_CR41","unstructured":"View. https:\/\/developer.android.com\/reference\/android\/view\/View Accessed 2024-08-28"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06384-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06384-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06384-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T19:31:37Z","timestamp":1758310297000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06384-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,24]]},"references-count":41,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["6384"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06384-7","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,2,24]]},"assertion":[{"value":"14 February 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"472"}}