{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:08Z","timestamp":1778051468724,"version":"3.51.4"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00118","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1147-1158","source":"Crossref","is-referenced-by-count":0,"title":["AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent"],"prefix":"10.1109","author":[{"given":"Neeraj","family":"Anand","sequence":"first","affiliation":[{"name":"Media and Data Science Research, Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rishabh","family":"Jain","sequence":"additional","affiliation":[{"name":"Media and Data Science Research, Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sohan","family":"Patnaik","sequence":"additional","affiliation":[{"name":"Media and Data Science Research, Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Balaji","family":"Krishnamurthy","sequence":"additional","affiliation":[{"name":"Media and Data Science Research, Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mausoom","family":"Sarkar","sequence":"additional","affiliation":[{"name":"Media and Data Science Research, Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480559"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref4","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref5","volume-title":"Introducing our multimodal models, 2023","volume":"2","author":"Bavishi","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06792-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.110"},{"key":"ref8","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.11"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1220"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref14","article-title":"Multimodal web navigation with instruction-finetuned foundation models","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Furuta"},{"key":"ref15","article-title":"A real-world webagent with planning, long context understanding, and program synthesis","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Gur"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671620"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3690682"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2264"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01816"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref28","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref30","article-title":"Omniparser for pure vision based GUI agent","author":"Lu","year":"2024","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.539"},{"key":"ref32","article-title":"Policy-focused agent-based modeling using rl behavioral models","author":"Osoba","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref34","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"CoRR"},{"key":"ref35","article-title":"Ui-tars: Pioneering automated gui interaction with native agents","author":"Qin","year":"2025"},{"key":"ref36","article-title":"Androidinthewild: A large-scale dataset for android device control","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Rawles"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_25"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.449"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.449"},{"key":"ref41","first-page":"5636","article-title":"Towards better semantic understanding of mobile interfaces","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Sunkara"},{"key":"ref42","first-page":"5636","article-title":"Towards better semantic understanding of mobile interfaces","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Sunkara"},{"key":"ref43","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref44","article-title":"Mobile-agent: Autonomous multi-modal mobile device agent with visual perception","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2020.125312"},{"key":"ref46","article-title":"Empowering LLM to use smartphone for intelligent task automation","author":"Wen","year":"2023","journal-title":"CoRR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888900008122"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.599"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref50","article-title":"Gpt-4v in wonderland: Large multimodal models for zero-shot smartphone gui navigation","author":"Yan","year":"2023"},{"key":"ref51","article-title":"A survey on multi-modal large language models","author":"Yin","year":"2023","journal-title":"CoRR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref53","article-title":"Appagent: Multimodal agents as smartphone users","author":"Zhang","year":"2023","journal-title":"CoRR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445186"},{"key":"ref55","article-title":"Beyond llava-hd: Diving into high-resolution large multimodal models","author":"Zhang","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.186"},{"key":"ref57","article-title":"Synapse: Leveraging few-shot exemplars for human-level computer control","author":"Zheng","year":"2023","journal-title":"CoRR"},{"key":"ref58","article-title":"Webarena: A realistic web environment for building autonomous agents","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Zhou"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492754.pdf?arnumber=11492754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:13:01Z","timestamp":1778047981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00118","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}