{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T06:32:26Z","timestamp":1782973946050,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T00:00:00Z","timestamp":1707177600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2022YFB3303300"],"award-info":[{"award-number":["2022YFB3303300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62207023"],"award-info":[{"award-number":["62207023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Ng Teng Fong Charitable Foundation in the form of ZJU-SUTD IDEA Grant","award":["188170-11102"],"award-info":[{"award-number":["188170-11102"]}]},{"name":"Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,2,6]]},"DOI":"10.1145\/3597503.3623313","type":"proceedings-article","created":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T20:53:16Z","timestamp":1707252796000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["EGFE: End-to-end Grouping of Fragmented Elements in UI Designs with Multimodal Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9049-0394","authenticated-orcid":false,"given":"Liuqing","family":"Chen","sequence":"first","affiliation":[{"name":"Zhejiang University, Zhejiang, China"},{"name":"Zhejiang-Singapore Innovation and AI Joint Research Lab, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0127-3276","authenticated-orcid":false,"given":"Yunnong","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0615-0607","authenticated-orcid":false,"given":"Shuhong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2664-4386","authenticated-orcid":false,"given":"Yaxuan","family":"Song","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5561-0493","authenticated-orcid":false,"given":"Lingyun","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"},{"name":"Zhejiang-Singapore Innovation and AI Joint Research Lab, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7153-1090","authenticated-orcid":false,"given":"Yankun","family":"Zhen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5977-1115","authenticated-orcid":false,"given":"Tingting","family":"Zhou","sequence":"additional","affiliation":[{"name":"Alibaba Group, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0085-1856","authenticated-orcid":false,"given":"Yanfang","family":"Chang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,2,6]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Accessibility - Vision. Website. https:\/\/www.apple.com\/accessibility\/vision\/ [Accessed on","year":"2022","unstructured":"apple. 2022. Accessibility - Vision. Website. https:\/\/www.apple.com\/accessibility\/vision\/ [Accessed on Dec. 27, 2022]."},{"key":"e_1_3_2_1_2_1","volume-title":"Uibert: Learning generic multimodal representations for ui understanding. arXiv preprint arXiv:2107.13731","author":"Bai Chongyang","year":"2021","unstructured":"Chongyang Bai, Xiaoxue Zang, Ying Xu, Srinivas Sunkara, Abhinav Rastogi, Jindong Chen, et al. 2021. Uibert: Learning generic multimodal representations for ui understanding. arXiv preprint arXiv:2107.13731 (2021)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3220134.3220135"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445762"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180240"},{"key":"e_1_3_2_1_7_1","volume-title":"Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination? Association for Computing Machinery","author":"Chen Jieshan","unstructured":"Jieshan Chen, Mulong Xie, Zhenchang Xing, Chunyang Chen, Xiwei Xu, Liming Zhu, and Guoqiang Li. 2020. Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination? Association for Computing Machinery, New York, NY, USA, 1202--1214."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/AI4Mobile.2019.8672718"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2200099"},{"key":"e_1_3_2_1_10_1","volume-title":"Codefun platform. https:\/\/code.fun\/ [Accessed on","author":"Codefun","year":"2022","unstructured":"Codefun 2022. Codefun platform. https:\/\/code.fun\/ [Accessed on Dec. 27, 2022]."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Chang Ming-Wei","year":"2019","unstructured":"JacobDevlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171--4186."},{"key":"e_1_3_2_1_12_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR (2021)."},{"key":"e_1_3_2_1_13_1","volume-title":"Wilcoxon-Mann-Whitney or t-test? On assumptions for hypothesis tests and multiple interpretations of decision rules. Statistics surveys 4","author":"Fay Michael P","year":"2010","unstructured":"Michael P Fay and Michael A Proschan. 2010. Wilcoxon-Mann-Whitney or t-test? On assumptions for hypothesis tests and multiple interpretations of decision rules. Statistics surveys 4 (2010), 1."},{"key":"e_1_3_2_1_14_1","volume-title":"Figma platform. https:\/\/www.figma.com\/ [Accessed on","year":"2022","unstructured":"figma. 2022. Figma platform. https:\/\/www.figma.com\/ [Accessed on Dec. 27, 2022]."},{"key":"e_1_3_2_1_15_1","volume-title":"Gestalt psychology. https:\/\/en.wikipedia.org\/wiki\/Gestalt_psychology#ite_note-1 [Accessed on","year":"2022","unstructured":"Gestalt. 1967. Gestalt psychology. https:\/\/en.wikipedia.org\/wiki\/Gestalt_psychology#ite_note-1 [Accessed on Dec. 27, 2022]."},{"key":"e_1_3_2_1_16_1","volume-title":"Get started on Android with TalkBack - Android Accessibility Help. Website. https:\/\/support.google.com\/accessibility\/android\/answer\/6283677?hl=en [Accessed on","year":"2022","unstructured":"Google. 2022. Get started on Android with TalkBack - Android Accessibility Help. Website. https:\/\/support.google.com\/accessibility\/android\/answer\/6283677?hl=en [Accessed on Dec. 12, 2022]."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16741"},{"key":"e_1_3_2_1_19_1","volume-title":"Intelligent Code Generation for Design Drafts. https:\/\/www.imgcook.com\/ [Accessed on","year":"2022","unstructured":"Imgcook. 2022. Intelligent Code Generation for Design Drafts. https:\/\/www.imgcook.com\/ [Accessed on Dec. 27, 2022]."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502042"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2208.06658"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242650"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416547"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_26_1","volume-title":"https:\/\/pytorch.org\/ [Accessed on","author":"Pytorch Framework Meta","year":"2022","unstructured":"Meta platforms. 2022. Pytorch Framework. https:\/\/pytorch.org\/ [Accessed on Dec. 27, 2022]."},{"key":"e_1_3_2_1_27_1","volume-title":"vscode. https:\/\/code.visualstudio.com [Accessed on","year":"2022","unstructured":"Microsoft. 2022. vscode. https:\/\/code.visualstudio.com [Accessed on Dec. 12, 2022]."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2018.2844788"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180246"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2015.32"},{"key":"e_1_3_2_1_31_1","volume-title":"Sketch2code: Generating a website from a paper mockup. ArXiv abs\/1905.13750","author":"Robinson Alex","year":"2019","unstructured":"Alex Robinson. 2019. Sketch2code: Generating a website from a paper mockup. ArXiv abs\/1905.13750 (2019)."},{"key":"e_1_3_2_1_32_1","volume-title":"Sketch Command-line interface. https:\/\/developer.sketch.com\/cli\/ [Accessed on","year":"2022","unstructured":"Sketch. 2022. Sketch Command-line interface. https:\/\/developer.sketch.com\/cli\/ [Accessed on Dec. 27, 2022]."},{"key":"e_1_3_2_1_33_1","volume-title":"Sketch software. https:\/\/www.sketch.com\/ [Accessed on","year":"2022","unstructured":"Sketch. 2022. Sketch software. https:\/\/www.sketch.com\/ [Accessed on Dec. 27, 2022]."},{"key":"e_1_3_2_1_34_1","volume-title":"Workshops at the Twenty-Sixth AAAI Conference on Artificial Intelligence.","author":"Su Hao","year":"2012","unstructured":"Hao Su, Jia Deng, and Li Fei-Fei. 2012. Crowdsourcing annotations for visual object detection. In Workshops at the Twenty-Sixth AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on machine learning. PMLR, 6105--6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105--6114."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417940"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549138"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447526.3472064"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445186"}],"event":{"name":"ICSE '24: IEEE\/ACM 46th International Conference on Software Engineering","location":"Lisbon Portugal","acronym":"ICSE '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3623313","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3623313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:45Z","timestamp":1750182525000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3623313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,6]]},"references-count":39,"alternative-id":["10.1145\/3597503.3623313","10.1145\/3597503"],"URL":"https:\/\/doi.org\/10.1145\/3597503.3623313","relation":{},"subject":[],"published":{"date-parts":[[2024,2,6]]},"assertion":[{"value":"2024-02-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}