{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:53:29Z","timestamp":1781816009513,"version":"3.54.5"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Zhejiang Pioneer (Jianbing) Project","award":["2025C01198"],"award-info":[{"award-number":["2025C01198"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372398"],"award-info":[{"award-number":["62372398"]}],"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":["72342025"],"award-info":[{"award-number":["72342025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Science Foundation of China","award":["LQK26F020002"],"award-info":[{"award-number":["LQK26F020002"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2025-00067"],"award-info":[{"award-number":["226-2025-00067"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tse.2026.3688725","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:49:20Z","timestamp":1777492160000},"page":"1944-1959","source":"Crossref","is-referenced-by-count":0,"title":["GUIGroup: Enabling Functional Layout Grouping With Multimodal Large Language Models"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3891-9336","authenticated-orcid":false,"given":"Yulei","family":"Zhang","sequence":"first","affiliation":[{"name":"The State Key Laboratory of Blockchain and Data Security, College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4643-9691","authenticated-orcid":false,"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Blockchain and Data Security, College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6212-6313","authenticated-orcid":false,"given":"Zejun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2991-2744","authenticated-orcid":false,"given":"Xiaoqian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0145-615X","authenticated-orcid":false,"given":"Kui","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7663-1421","authenticated-orcid":false,"given":"Zhenchang","family":"Xing","sequence":"additional","affiliation":[{"name":"CSIRO’s Data61 and Australian National University, Canberra, ACT, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6302-3256","authenticated-orcid":false,"given":"Xin","family":"Xia","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Blockchain and Data Security, College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1846-0921","authenticated-orcid":false,"given":"Lingfeng","family":"Bao","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Blockchain and Data Security, College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Atomic Design.","author":"Frost","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445186"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549138"},{"key":"ref4","article-title":"UI design in practice: Gestalt principles."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2024.102679"},{"key":"ref6","volume-title":"GPT-4V(ision) system card.","year":"2023"},{"key":"ref7","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref8","article-title":"The Claude 3 model family: Opus, Sonnet, Haiku","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_14"},{"key":"ref10","article-title":"Navigating the digital world as humans do: Universal visual grounding for GUI agents","author":"Gou","year":"2024"},{"key":"ref11","article-title":"GPT-4V (ision) is a generalist web agent, if grounded","author":"Zheng","year":"2024"},{"key":"ref12","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V","author":"Yang","year":"2023"},{"key":"ref13","article-title":"UI-vision: A desktop-centric GUI benchmark for visual perception and interaction","author":"Nayak","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01859"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642350"},{"key":"ref16","volume-title":"PaddleOCR, awesome multilingual OCR toolkits based on PaddlePaddle."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3728909"},{"key":"ref19","article-title":"OmniParser for pure vision based GUI agent","author":"Lu","year":"2024"},{"key":"ref20","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3715726"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126651"},{"key":"ref23","volume-title":"Apply crap to design: S1t2 blog."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676386"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3728925"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i39.40606"},{"key":"ref28","article-title":"V2P: From background suppression to center peaking for robust GUI grounding task","author":"Chen","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180240"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450671"},{"key":"ref32","article-title":"Automatically generating UI code from screenshot: A divide-and-conquer-based approach","author":"Wan","year":"2024"},{"key":"ref33","article-title":"A rule-based approach for UI migration from Android to iOS","author":"Gao","year":"2024"},{"key":"ref34","first-page":"59860","article-title":"Pairwise GUI dataset construction between Android phones and tablets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhan","year":"2023"},{"key":"ref35","article-title":"DeskVision: Large scale desktop region captioning for advanced GUI agents","author":"Xu","year":"2025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623313"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417940"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409691"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2200099"},{"key":"ref40","article-title":"ULDGNN: A fragmented UI layer detector based on graph neural networks","author":"Li","year":"2022"},{"key":"ref41","author":"Yongxin","year":"2019","journal-title":"UI2code: How to fine-tune background and foreground analysis"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2015.32"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref44","article-title":"UI-TARS: Pioneering automated GUI interaction with native agents","author":"Qin","year":"2025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"ref46","article-title":"Ferret-UI 2: Mastering universal user interface understanding across platforms","author":"Li","year":"2024"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/32\/11563955\/11499425.pdf?arnumber=11499425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:10:20Z","timestamp":1781813420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11499425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":46,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tse.2026.3688725","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"value":"0098-5589","type":"print"},{"value":"1939-3520","type":"electronic"},{"value":"2326-3881","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}