{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:11:43Z","timestamp":1783764703178,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3786583.3786892","type":"proceedings-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T09:12:14Z","timestamp":1783761134000},"page":"508-519","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["XBIDetective: Leveraging Vision Language Models for Identifying Cross-Browser Visual Inconsistencies"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2068-9306","authenticated-orcid":false,"given":"Balreet","family":"Grewal","sequence":"first","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1965-1771","authenticated-orcid":false,"given":"James","family":"Graham","sequence":"additional","affiliation":[{"name":"Mozilla Corporation, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7589-6496","authenticated-orcid":false,"given":"Jeff","family":"Muizelaar","sequence":"additional","affiliation":[{"name":"Mozilla Corporation, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9356-8203","authenticated-orcid":false,"given":"Jan","family":"Odv\u00e1rko","sequence":"additional","affiliation":[{"name":"Independent Researcher, Ceske Budejovice, Czech Republic"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2738-1387","authenticated-orcid":false,"given":"Suhaib","family":"Mujahid","sequence":"additional","affiliation":[{"name":"Mozilla Corporation, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3285-5121","authenticated-orcid":false,"given":"Marco","family":"Castelluccio","sequence":"additional","affiliation":[{"name":"Mozilla Corporation, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0474-5718","authenticated-orcid":false,"given":"Cor-Paul","family":"Bezemer","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,11]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2019.00027"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Luca Ardito Andrea Bottino Riccardo Coppola Fabrizio Lamberti Francesco Manigrasso Lia Morra and Marco Torchiano. 2021. Feature matching-based approaches to improve the robustness of Android visual GUI testing. ACM Transactions on Software Engineering and Methodology (TOSEM) 31 2 (2021) 1\u201332.","DOI":"10.1145\/3477427"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Zhe Cao Gines Hidalgo Tomas Simon Shih-En Wei and Yaser Sheikh. 2019. Openpose: Realtime multi-person 2d pose estimation using part affinity fields. IEEE transactions on pattern analysis and machine intelligence 43 1 (2019) 172\u2013186.","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2012.97"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.2010.5609723"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35702-2_5"},{"key":"e_1_3_3_2_8_2","unstructured":"Biniam\u00a0Fisseha Demissie Yan\u00a0Naing Tun Lwin\u00a0Khin Shar and Mariano Ceccato. 2025. VLM-Fuzz: Vision Language Model Assisted Recursive Depth-first Search Exploration for Effective UI Testing of Android Apps. arxiv:https:\/\/arXiv.org\/abs\/2504.11675\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2504.11675"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00084"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.6084\/m9.figshare.30223654"},{"key":"e_1_3_3_2_11_2","volume-title":"Understanding Headless vs. Headed Modes in Playwright: A Guide for QA Automation Engineers \/ SDETs","author":"Jr Juan G.\u00a0Vazquez","year":"2025","unstructured":"Juan G.\u00a0Vazquez Jr. 2025. Understanding Headless vs. Headed Modes in Playwright: A Guide for QA Automation Engineers \/ SDETs. https:\/\/medium.com\/@JohnnyV_5G\/understanding-headless-vs-headed-modes-in-playwright-a-guide-for-qa-automation-engineers-sdets-153452e65cbf Accessed: 2025-09-24."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/APSEC65559.2024.00017"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3613867"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Ruofan Liu Xiwen Teoh Yun Lin Guanjie Chen Ruofei Ren Denys Poshyvanyk and Jin\u00a0Song Dong. 2025. GUIPilot: A Consistency-Based Mobile GUI Testing Approach for Detecting Application-Specific Bugs. Proc. ACM Softw. Eng. 2 ISSTA Article ISSTA034 (June 2025) 24\u00a0pages. 10.1145\/3728909","DOI":"10.1145\/3728909"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639180"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416547"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Zhe Liu Chunyang Chen Junjie Wang Yuekai Huang Jun Hu and Qing Wang. 2023. Nighthawk: Fully Automated Localizing UI Display Issues via Visual Understanding. IEEE Transactions on Software Engineering 49 1 (2023) 403\u2013418. 10.1109\/TSE.2022.3150876","DOI":"10.1109\/TSE.2022.3150876"},{"key":"e_1_3_3_2_18_2","unstructured":"Zhe Liu Cheng Li Chunyang Chen Junjie Wang Mengzhuo Chen Boyu Wu Yawen Wang Jun Hu and Qing Wang. 2024. Seeing is Believing: Vision-driven Non-crash Functional Bug Detection for Mobile Apps. arxiv:https:\/\/arXiv.org\/abs\/2407.03037\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2407.03037"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICST49551.2021.00062"},{"key":"e_1_3_3_2_20_2","unstructured":"Wentao Lu Alexander Senchenko Abram Hindle and Cor-Paul Bezemer. 2025. Automated Bug Frame Retrieval from Gameplay Videos Using Vision-Language Models. arxiv:https:\/\/arXiv.org\/abs\/2508.04895\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2508.04895"},{"key":"e_1_3_3_2_21_2","unstructured":"Finlay Macklon and Cor-Paul Bezemer. 2025. Exploring the Capabilities of Vision-Language Models to Detect Visual Bugs in HTML5 <canvas> Applications. arxiv:https:\/\/arXiv.org\/abs\/2501.09236\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2501.09236"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556913"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3092703.3098223"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2015.7102586"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2015.7102638"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2593833.2593836"},{"key":"e_1_3_3_2_27_2","volume-title":"Introduction to Cross-Browser Testing","author":"contributors MDN","year":"2025","unstructured":"MDN contributors. 2025. Introduction to Cross-Browser Testing. https:\/\/developer.mozilla.org\/en-US\/docs\/Learn_web_development\/Extensions\/Testing\/Introduction Accessed: 2025-08-11."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASEW52652.2021.00024"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628057"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"T\u00f5nis Saar Marlon Dumas Marti Kaljuve and Nataliia Semenenko. 2016. Browserbite: cross-browser testing via image processing. Software: Practice and Experience 46 11 (2016) 1459\u20131477.","DOI":"10.1002\/spe.2387"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Leandro\u00a0N Sabaren Maximiliano\u00a0Agust\u00edn Mascheroni Cristina\u00a0L Greiner and Emanuel Irraz\u00e1bal. 2018. A systematic literature review in cross-browser testing. Journal of Computer Science & Technology 18 (2018).","DOI":"10.24215\/16666038.18.e03"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.2013.88"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510044"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616336"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236063"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00144"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02118"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Mohammad\u00a0Reza Taesiri Abhijay Ghildyal Saman Zadtootaghaj Nabajeet Barman and Cor-Paul Bezemer. 2025. VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance. https:\/\/arxiv.org\/abs\/2505.15952. 10.48550\/arXiv.2505.15952","DOI":"10.48550\/arXiv.2505.15952"},{"key":"e_1_3_3_2_39_2","unstructured":"Mohammad\u00a0Reza Taesiri Finlay Macklon Yihe Wang Hengshuo Shen and Cor-Paul Bezemer. 2022. Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors. arxiv:https:\/\/arXiv.org\/abs\/2210.02506\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2210.02506"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Haruto Tanno Yu Adachi Yu Yoshimura Katsuyuki Natsukawa and Hideya Iwasaki. 2020. Region-based detection of essential differences in image-based visual regression testing. Journal of Information Processing 28 (2020) 268\u2013278.","DOI":"10.2197\/ipsjjip.28.268"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"J Tuovenen Mourad Oussalah and Panos Kostakos. 2019. MAuto: Automatic mobile game testing tool using image-matching based approach. The Computer Games Journal 8 3 (2019) 215\u2013239.","DOI":"10.1007\/s40869-019-00087-z"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3092703.3098221"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME58944.2024.00022"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","unstructured":"Willian\u00a0Massami Watanabe Giovana\u00a0L\u00e1zaro Am\u00eandola and Fagner\u00a0Christian Paes. 2019. Layout Cross-Platform and Cross-Browser Incompatibilities Detection using Classification of DOM Elements. ACM Trans. Web 13 2 Article 12 (March 2019) 27\u00a0pages. 10.1145\/3316808","DOI":"10.1145\/3316808"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Willian\u00a0Massami Watanabe Danilo\u00a0Alves dos Santos and Claiton de Oliveira. 2023. Layout Cross-Browser Failure Classification for Mobile Responsive Design Web Applications: Combining Classification Models Using Feature Selection. ACM Transactions on the Web 17 4 (2023) 1\u201334.","DOI":"10.1145\/3580518"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417940"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS.2018.00016"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-Companion52605.2021.00043"},{"key":"e_1_3_3_2_49_2","first-page":"153","volume-title":"2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE)","author":"Zhou Chijin","year":"2024","unstructured":"Chijin Zhou, Quan Zhang, Bingzhou Qian, and Yu Jiang. 2024. Janus: Detecting Rendering Bugs in Web Browsers via Visual Delta Consistency. In 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE). IEEE Computer Society, 153\u2013164."}],"event":{"name":"ICSE-SEIP '26: 2026 IEEE\/ACM 48th International Conference on Software Engineering","location":"Rio de Janeiro Brazil","acronym":"ICSE-SEIP '26","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 48th International Conference on Software Engineering: Software Engineering in Practice"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786583.3786892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T09:13:51Z","timestamp":1783761231000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786583.3786892"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":48,"alternative-id":["10.1145\/3786583.3786892","10.1145\/3786583"],"URL":"https:\/\/doi.org\/10.1145\/3786583.3786892","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}