{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:08:41Z","timestamp":1784308121417,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755688","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"8778-8786","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9842-3552","authenticated-orcid":false,"given":"Kaixin","family":"Li","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5379-8461","authenticated-orcid":false,"given":"Ziyang","family":"Meng","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4111-8334","authenticated-orcid":false,"given":"Hongzhan","family":"Lin","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6037-0471","authenticated-orcid":false,"given":"Ziyang","family":"Luo","sequence":"additional","affiliation":[{"name":"Salesforce Research, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1437-0270","authenticated-orcid":false,"given":"Yuchen","family":"Tian","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7464-8331","authenticated-orcid":false,"given":"Jing","family":"Ma","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1931-7775","authenticated-orcid":false,"given":"Zhiyong","family":"Huang","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966, Vol. 1, 2 (2023), 3."},{"key":"e_1_3_2_1_2_1","volume-title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks. arXiv preprint arXiv:2312.14238","author":"Chen Zhe","year":"2023","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, and Jifeng Dai. 2023. InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks. arXiv preprint arXiv:2312.14238 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Kanzhi Cheng Qiushi Sun Yougang Chu Fangzhi Xu Yantao Li Jianbing Zhang and Zhiyong Wu. 2024. SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents. arXiv:2401.10935 [cs.HC] https:\/\/arxiv.org\/abs\/2401.10935","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"e_1_3_2_1_4_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Deng Xiang","year":"2024","unstructured":"Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2024. Mind2web: Towards a generalist agent for the web. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_5_1","unstructured":"Boyu Gou Ruohan Wang Boyuan Zheng Yanan Xie Cheng Chang Yiheng Shu Huan Sun and Yu Su. 2024. Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents. arXiv:2410.05243 [cs.AI] https:\/\/arxiv.org\/abs\/2410.05243"},{"key":"e_1_3_2_1_6_1","volume-title":"Mustafa Safdari, Yutaka Matsuo, Douglas Eck, and Aleksandra Faust.","author":"Gur Izzeddin","year":"2024","unstructured":"Izzeddin Gur, Hiroki Furuta, Austin V. Huang, Mustafa Safdari, Yutaka Matsuo, Douglas Eck, and Aleksandra Faust. 2024. A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis. In ICLR. https:\/\/openreview.net\/forum?id=9JQtrumvg8"},{"key":"e_1_3_2_1_7_1","volume-title":"WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models. arXiv preprint arXiv:2401.13919","author":"He Hongliang","year":"2024","unstructured":"Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, and Dong Yu. 2024. WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models. arXiv preprint arXiv:2401.13919 (2024)."},{"key":"e_1_3_2_1_8_1","unstructured":"Wenyi Hong Weihan Wang Qingsong Lv Jiazheng Xu Wenmeng Yu Junhui Ji Yan Wang Zihan Wang Yuxuan Zhang Juanzi Li Bin Xu Yuxiao Dong Ming Ding and Jie Tang. 2023. CogAgent: A Visual Language Model for GUI Agents. arXiv:2312.08914 [cs.CV] https:\/\/arxiv.org\/abs\/2312.08914"},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Machine Learning. PMLR, 9466-9482","author":"Humphreys Peter C","year":"2022","unstructured":"Peter C Humphreys, David Raposo, Tobias Pohlen, Gregory Thornton, Rachita Chhaparia, Alistair Muldal, Josh Abramson, Petko Georgiev, Adam Santoro, and Timothy Lillicrap. 2022. A data-driven approach for learning to control computers. In International Conference on Machine Learning. PMLR, 9466-9482."},{"key":"e_1_3_2_1_10_1","volume-title":"Po-Yu Huang","author":"Koh Jing Yu","year":"2024","unstructured":"Jing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur, Ming Chong Lim, Po-Yu Huang, Graham Neubig, Shuyan Zhou, Ruslan Salakhutdinov, and Daniel Fried. 2024. VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks. ACL (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326","author":"Li Bo","year":"2024","unstructured":"Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, et al., 2024a. Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Appagent v2: Advanced agent for flexible mobile interactions. arXiv preprint arXiv:2408.11824","author":"Li Yanda","year":"2024","unstructured":"Yanda Li, Chi Zhang, Wanqi Yang, Bin Fu, Pei Cheng, Xin Chen, Ling Chen, and Yunchao Wei. 2024b. Appagent v2: Advanced agent for flexible mobile interactions. arXiv preprint arXiv:2408.11824 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent. arXiv preprint arXiv:2411.17465","author":"Lin Kevin Qinghong","year":"2024","unstructured":"Kevin Qinghong Lin, Linjie Li, Difei Gao, Zhengyuan Yang, Shiwei Wu, Zechen Bai, Weixian Lei, Lijuan Wang, and Mike Zheng Shou. 2024. ShowUI: One Vision-Language-Action Model for GUI Visual Agent. arXiv preprint arXiv:2411.17465 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_15_1","volume-title":"Wai Lam, Graham Neubig, Yuanzhi Li, and Xiang Yue.","author":"Liu Junpeng","year":"2024","unstructured":"Junpeng Liu, Yifan Song, Bill Yuchen Lin, Wai Lam, Graham Neubig, Yuanzhi Li, and Xiang Yue. 2024b. VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding? arXiv preprint arXiv:2404.05955 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Improved GUI Grounding via Iterative Narrowing. arXiv preprint arXiv:2411.13591","author":"Nguyen Anthony","year":"2024","unstructured":"Anthony Nguyen. 2024. Improved GUI Grounding via Iterative Narrowing. arXiv preprint arXiv:2411.13591 (2024)."},{"key":"e_1_3_2_1_17_1","unstructured":"OpenAI. 2023. GPT-4V(ision) System Card. https:\/\/cdn.openai.com\/papers\/GPTV_System_Card.pdf. Accessed: 2024-02-03."},{"key":"e_1_3_2_1_18_1","unstructured":"OpenAI. 2024. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/. Accessed: 2024-11-01."},{"key":"e_1_3_2_1_19_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"conquer and combine: A training-free framework for high-resolution image perception in multimodal large language models. arXiv preprint arXiv:2408.15556","author":"Wang Wenbin","year":"2024","unstructured":"Wenbin Wang, Liang Ding, Minyan Zeng, Xiabin Zhou, Li Shen, Yong Luo, and Dacheng Tao. 2024b. Divide, conquer and combine: A training-free framework for high-resolution image perception in multimodal large language models. arXiv preprint arXiv:2408.15556 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"Guided Visual Search as a Core Mechanism in Multimodal LLMs. arXiv preprint arXiv:2312.14135","author":"Wu Penghao","year":"2023","unstructured":"Penghao Wu and Saining Xie. 2023. V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs. arXiv preprint arXiv:2312.14135 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Paul Pu Liang, et al","author":"Wu Zhiyong","year":"2024","unstructured":"Zhiyong Wu, Zhenyu Wu, Fangzhi Xu, Yian Wang, Qiushi Sun, Chengyou Jia, Kanzhi Cheng, Zichen Ding, Liheng Chen, Paul Pu Liang, et al., 2024. OS-ATLAS: A Foundation Action Model for Generalist GUI Agents. arXiv preprint arXiv:2410.23218 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, and Tao Yu.","author":"Xie Tianbao","year":"2024","unstructured":"Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh Jing Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, and Tao Yu. 2024. OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments. arXiv:2404.07972 [cs.AI]"},{"key":"e_1_3_2_1_24_1","volume-title":"Aria-UI: Visual Grounding for GUI Instructions. arXiv preprint arXiv:2412.16256","author":"Yang Yuhao","year":"2024","unstructured":"Yuhao Yang, Yue Wang, Dongxu Li, Ziyang Luo, Bei Chen, Chao Huang, and Junnan Li. 2024. Aria-UI: Visual Grounding for GUI Instructions. arXiv preprint arXiv:2412.16256 (2024)."},{"key":"e_1_3_2_1_25_1","volume-title":"Appagent: Multimodal agents as smartphone users. arXiv preprint arXiv:2312.13771","author":"Yang Zhao","year":"2023","unstructured":"Zhao Yang, Jiaxuan Liu, Yucheng Han, Xin Chen, Zebiao Huang, Bin Fu, and Gang Yu. 2023. Appagent: Multimodal agents as smartphone users. arXiv preprint arXiv:2312.13771 (2023)."},{"key":"e_1_3_2_1_26_1","first-page":"20744","article-title":"Webshop: Towards scalable real-world web interaction with grounded language agents","volume":"35","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Howard Chen, John Yang, and Karthik Narasimhan. 2022. Webshop: Towards scalable real-world web interaction with grounded language agents. Advances in Neural Information Processing Systems, Vol. 35 (2022), 20744-20757.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","unstructured":"Yuan Yao Tianyu Yu Ao Zhang Chongyi Wang Junbo Cui Hongji Zhu Tianchi Cai Haoyu Li Weilin Zhao Zhihui He et al. 2024. MiniCPM-V: A GPT-4V Level MLLM on Your Phone. arXiv preprint arXiv:2408.01800 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Keen You Haotian Zhang Eldon Schoop Floris Weers Amanda Swearngin Jeffrey Nichols Yinfei Yang and Zhe Gan. 2024. Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs. arXiv:2404.05719 [cs.CV] https:\/\/arxiv.org\/abs\/2404.05719","DOI":"10.1007\/978-3-031-73039-9_14"},{"key":"e_1_3_2_1_29_1","volume-title":"Ufo: A ui-focused agent for windows os interaction. arXiv preprint arXiv:2402.07939","author":"Zhang Chaoyun","year":"2024","unstructured":"Chaoyun Zhang, Liqun Li, Shilin He, Xu Zhang, Bo Qiao, Si Qin, Minghua Ma, Yu Kang, Qingwei Lin, Saravan Rajmohan, et al., 2024. Ufo: A ui-focused agent for windows os interaction. arXiv preprint arXiv:2402.07939 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.68"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755688","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:08:32Z","timestamp":1765339712000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755688"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":30,"alternative-id":["10.1145\/3746027.3755688","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755688","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}