{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T05:07:38Z","timestamp":1767848858120,"version":"3.49.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T00:00:00Z","timestamp":1719187200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T00:00:00Z","timestamp":1719187200000},"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":[[2024,6,24]]},"DOI":"10.1109\/ur61395.2024.10597464","type":"proceedings-article","created":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T17:23:58Z","timestamp":1722014638000},"page":"281-288","source":"Crossref","is-referenced-by-count":7,"title":["Is It Safe to Cross? Interpretable Risk Assessment with GPT-4V for Safety-Aware Street Crossing"],"prefix":"10.1109","author":[{"given":"Hochul","family":"Hwang","sequence":"first","affiliation":[{"name":"Manning College of Information and Computer Sciences, University of Massachusetts Amherst,Amherst,MA,U.S.,01002"}]},{"given":"Sunjae","family":"Kwon","sequence":"additional","affiliation":[{"name":"Manning College of Information and Computer Sciences, University of Massachusetts Amherst,Amherst,MA,U.S.,01002"}]},{"given":"Yekyung","family":"Kim","sequence":"additional","affiliation":[{"name":"Manning College of Information and Computer Sciences, University of Massachusetts Amherst,Amherst,MA,U.S.,01002"}]},{"given":"Donghyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Manning College of Information and Computer Sciences, University of Massachusetts Amherst,Amherst,MA,U.S.,01002"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2024.3400831"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning. PMLR","author":"Radford","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref7","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0145482X8908300910"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.11-9340"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-947X(2005)131:11(812)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISSSR56778.2022.00041"},{"key":"ref15","article-title":"Dragon: A dialogue-based robot for assistive navigation with visual language grounding","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353771"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3522757"},{"key":"ref18","volume-title":"Meet oko - the ai-powered navigation app for all pedestrians","year":"2023"},{"key":"ref19","volume-title":"Be my eyes - see the world together","author":"Eyes","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.04.003"},{"issue":"07","key":"ref21","article-title":"Guiding ai with human intuition for solving mathematical problems in chat gpt","volume":"11","author":"Poola","year":"2023","journal-title":"Journal Homepage"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1583","DOI":"10.18653\/v1\/2023.acl-long.88","article-title":"Vision meets definitions: Unsupervised visual word sense disambiguation incorporating gloss information","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Kwon","year":"2023"},{"key":"ref23","article-title":"Capabilities of gpt-4 on medical challenge problems","author":"Nori","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"74","article-title":"Breaking the bank with chatgpt: Few-shot text classification for finance","volume-title":"Proceedings of the Fifth Workshop on Financial Technology and Natural Language Processing and the Second Multimodal AI For Financial Forecasting","author":"Liang","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120"},{"key":"ref26","article-title":"Alpacafarm: A simulation framework for methods that learn from human feedback","volume":"abs\/2305.14387","author":"Dubois","year":"2023","journal-title":"ArXiv"},{"key":"ref27","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"abs\/2306.05685","author":"Zheng","year":"2023","journal-title":"ArXiv"},{"key":"ref28","article-title":"Factscore: Fine-grained atomic evaluation of factual precision in long form text generation","volume":"abs\/2305.14251","author":"Min","year":"2023","journal-title":"ArXiv"},{"key":"ref29","article-title":"G-eval: Nlg evaluation using gpt-4 with better human alignment","volume":"abs\/2303.16634","author":"Liu","year":"2023","journal-title":"ArXiv"},{"key":"ref30","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Next-gpt: Any-to-any multimodal Ilm","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Minigpt-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920961809"},{"key":"ref34","first-page":"674","article-title":"An iterative image registration technique. with an application to stereo vision","volume-title":"IJCAI\u2019 81: 7th international joint conference on Artificial intelligence","volume":"2","author":"Lucas","year":"1981"},{"key":"ref35","article-title":"Yolov4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref36","volume-title":"YOLO by Ultralytics","author":"Jocher","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/iros45743.2020.9340734"},{"key":"ref39","article-title":"Chain of thought prompting elicits reasoning in large language models","volume":"abs\/2201.1 1903","author":"Wei","year":"2022","journal-title":"ArXiv"}],"event":{"name":"2024 21st International Conference on Ubiquitous Robots (UR)","location":"New York, NY, USA","start":{"date-parts":[[2024,6,24]]},"end":{"date-parts":[[2024,6,27]]}},"container-title":["2024 21st International Conference on Ubiquitous Robots (UR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10597436\/10597437\/10597464.pdf?arnumber=10597464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T05:28:37Z","timestamp":1722058117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10597464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,24]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ur61395.2024.10597464","relation":{},"subject":[],"published":{"date-parts":[[2024,6,24]]}}}