{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:32:06Z","timestamp":1782408726528,"version":"3.54.5"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"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":[[2024,12,10]]},"DOI":"10.1109\/robio64047.2024.10907500","type":"proceedings-article","created":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:33:40Z","timestamp":1741372420000},"page":"1271-1275","source":"Crossref","is-referenced-by-count":4,"title":["Multimodal Knowledge Graph Vision-Language Models for Precision Retrieval and Inference in Embedded Systems"],"prefix":"10.1109","author":[{"given":"Mingyi","family":"Li","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology,Beijing,China,100081"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computing and Data Science, Xiamen University Malaysia,Selangor,Malaysia,43900"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology,Beijing,China,100081"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijin","family":"Han","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology,Beijing,China,100081"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dengting","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology,Beijing,China,100081"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zekun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Zhangjiang Institute of Mathematicas, Zhangjiang Institute of Shanghai,Shanghai,China,201203"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zong","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology,Beijing,China,100081"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoshuai","family":"Liu","sequence":"additional","affiliation":[{"name":"China North Vehicle Research Institute,General Technology Department,China,100072"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongfeng","family":"Jin","sequence":"additional","affiliation":[{"name":"Coordination Center of China,GNational Computer Network Emergency Response Technical Team,China,100083"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref2","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"*Advances in Neural Information Processing Systems*"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref5","volume-title":"Arkitscenes: A diverse real-world dataset for 3d indoor scene understanding using mobile rgb-d data","author":"Baruch","year":"2021"},{"key":"ref6","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref7","volume-title":"Objectnav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020"},{"key":"ref8","volume-title":"D3net: A speaker-listener architecture for semi-supervised dense captioning and visual grounding in rgb-d scans","author":"Chen","year":"2021"},{"key":"ref9","article-title":"Learning transferable visual models from natural language supervision","volume-title":"*Proceedings of the 38th International Conference on Machine Learning*","author":"Radford","year":"2021"},{"key":"ref10","volume-title":"Knowledge-augmented visual question answering","author":"Schwenk","year":"2022"},{"key":"ref11","author":"Gao","year":"2022","journal-title":"Multi-modal retrieval and generation in vision-and-language models"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.772"},{"key":"ref13","volume-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023"},{"key":"ref14","article-title":"Mobility VLA: Integrating Vision-Language Models with Long-Context Data","volume-title":"*Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition*","author":"Chiang","year":"2024"},{"key":"ref15","article-title":"Bridging LLM Planning and VLM for Real-Time Decision-Making","volume-title":"*Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition*","author":"Cai","year":"2024"}],"event":{"name":"2024 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Bangkok, Thailand","start":{"date-parts":[[2024,12,10]]},"end":{"date-parts":[[2024,12,14]]}},"container-title":["2024 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10906779\/10907273\/10907500.pdf?arnumber=10907500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,8]],"date-time":"2025-03-08T08:16:41Z","timestamp":1741421801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10907500\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/robio64047.2024.10907500","relation":{},"subject":[],"published":{"date-parts":[[2024,12,10]]}}}