{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T22:14:35Z","timestamp":1778278475978,"version":"3.51.4"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730382","type":"print"},{"value":"9783031730399","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73039-9_14","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:57:07Z","timestamp":1730300227000},"page":"240-255","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Ferret-UI: Grounded Mobile UI Understanding with\u00a0Multimodal LLMs"],"prefix":"10.1007","author":[{"given":"Keen","family":"You","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haotian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eldon","family":"Schoop","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Floris","family":"Weers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amanda","family":"Swearngin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeffrey","family":"Nichols","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinfei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Gan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"14_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Amalfitano, D., Fasolino, A.R., Tramontana, P.: A GUI crawling-based technique for android mobile application testing. In: 2011 IEEE Fourth International Conference on Software Testing, Verification and Validation Workshops, pp. 252\u2013261. IEEE (2011)","DOI":"10.1109\/ICSTW.2011.77"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Bai, C., et al.: UIBert: learning generic multimodal representations for UI understanding (2021)","DOI":"10.24963\/ijcai.2021\/235"},{"key":"14_CR4","unstructured":"Bavishi, R., et al.: Introducing our multimodal models (2023). https:\/\/www.adept.ai\/blog\/fuyu-8b"},{"key":"14_CR5","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal LLM\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)"},{"issue":"1","key":"14_CR6","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1145\/208143.208161","volume":"2","author":"WK Edwards","year":"1995","unstructured":"Edwards, W.K., Mynatt, E.D., Stockton, K.: Access to graphical interfaces for blind users. Interactions 2(1), 54\u201367 (1995)","journal-title":"Interactions"},{"key":"14_CR7","unstructured":"Gao, P., et al.: SPHINX-X: scaling data and parameters for a family of multi-modal large language models (2024)"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Hong, W., et\u00a0al.: CogAgent: a visual language model for GUI agents. arXiv preprint arXiv:2312.08914 (2023)","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"14_CR9","unstructured":"Jiang, Y., Schoop, E., Swearngin, A., Nichols, J.: ILuvUI: instruction-tuned language-vision modeling of UIs from machine conversations (2023)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Kuang, R., Gong, J., Yin, H., Lyu, Y., Zhang, X.: What makes a great mobile app? A quantitative study using a new mobile crawler. In: 2018 IEEE Symposium on Service-Oriented System Engineering (SOSE), pp. 222\u2013227. IEEE (2018)","DOI":"10.1109\/SOSE.2018.00037"},{"key":"14_CR11","unstructured":"Lee, K., et al.: Pix2Struct: screenshot parsing as pretraining for visual language understanding. In: ICML (2023)"},{"key":"14_CR12","unstructured":"Li, G., Li, Y.: Spotlight: mobile UI understanding using vision-language models with a focus (2023)"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Monkey: Image resolution and text label are important things for large multi-modal models. arXiv preprint arXiv:2311.06607 (2023)","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: SPHINX: the joint mixing of weights, tasks, and visual embeddings for multi-modal large language models (2023)","DOI":"10.1007\/978-3-031-73033-7_3"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Linares-V\u00e1squez, M., Moran, K., Poshyvanyk, D.: Continuous, evolutionary and large-scale: a new perspective for automated mobile app testing. In: 2017 IEEE International Conference on Software Maintenance and Evolution (ICSME), pp. 399\u2013410. IEEE (2017)","DOI":"10.1109\/ICSME.2017.27"},{"key":"14_CR16","unstructured":"Liu, H., et al.: LLaVA-next: improved reasoning, OCR, and world knowledge, January 2024. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"14_CR17","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"14_CR18","unstructured":"Liu, Y., et al.: On the hidden mystery of OCR in large multimodal models (2024)"},{"key":"14_CR19","unstructured":"OpenAI: Achiam, J., et\u00a0al.: GPT-4 technical report (2024)"},{"key":"14_CR20","unstructured":"Peng, et al.: Kosmos-2: grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)"},{"key":"14_CR21","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR22","unstructured":"Wang, J., et al.: Mobile-agent: autonomous multi-modal mobile device agent with visual perception (2024)"},{"key":"14_CR23","unstructured":"Yan, A., et\u00a0al.: GPT-4V in wonderland: large multimodal models for zero-shot smartphone GUI navigation. arXiv preprint arXiv:2311.07562 (2023)"},{"key":"14_CR24","unstructured":"Yang, J., Zhang, H., Li, F., Zou, X., Li, C., Gao, J.: Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V. arXiv preprint arXiv:2310.11441 (2023)"},{"key":"14_CR25","unstructured":"Yang, Z., et al.: The dawn of LMMs: preliminary explorations with GPT-4v(ision) (2023)"},{"key":"14_CR26","unstructured":"You, H., et al.: FERRET: refer and ground anything anywhere at any granularity (2023)"},{"key":"14_CR27","unstructured":"Zhang, C., et al.: AppAgent: multimodal agents as smartphone users (2023)"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Screen recognition: creating accessibility metadata for mobile applications from pixels (2021)","DOI":"10.1145\/3411764.3445186"},{"key":"14_CR29","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with MT-bench and chatbot arena (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73039-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T14:15:21Z","timestamp":1732976121000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73039-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031730382","9783031730399"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73039-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}