{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T14:47:31Z","timestamp":1779374851209,"version":"3.53.1"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801813","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"221-228","source":"Crossref","is-referenced-by-count":4,"title":["A Large Vision-Language Model based Environment Perception System for Visually Impaired People"],"prefix":"10.1109","author":[{"given":"Zezhou","family":"Chen","sequence":"first","affiliation":[{"name":"China Unicom,AI Innovation Center,Beijing,China,100013"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"China Unicom,AI Innovation Center,Beijing,China,100013"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"China Unicom,AI Innovation Center,Beijing,China,100013"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kohou","family":"Wang","sequence":"additional","affiliation":[{"name":"China Unicom,AI Innovation Center,Beijing,China,100013"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiguo","family":"Lian","sequence":"additional","affiliation":[{"name":"China Unicom,AI Innovation Center,Beijing,China,100013"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"The perception of the environment: Essays in livelihood, dwelling and skill","author":"Ingold","year":"2000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989772"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S2214-109X(17)30293-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2023.2854"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2018.2812498"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/AIPR.2004.22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093353"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_33"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1255"},{"key":"ref11","article-title":"Check your facts and try again: Improving large language models with external knowledge and automated feedback","author":"Peng","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2017.014980"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2017.014832"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2017.015101"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/228347.228368"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173650"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025646"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858245"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858058"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173689"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173772"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173810"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025899"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025906"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173789"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2016.2614422"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173717"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"99","key":"ref34","first-page":"1","article-title":"Segnet: A deep convolutional encoder-decoder architecture for scene segmentation","volume":"PP","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref40","article-title":"Rednet: Residual encoder-decoder network for indoor rgb-d semantic segmentation","author":"Jiang","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.214"},{"key":"ref45","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"International Conference on Machine Learning","author":"Cho"},{"key":"ref46","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Tsimpoukelli"},{"key":"ref47","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021"},{"key":"ref48","article-title":"Visual instruction tuning","volume-title":"Advances in neural information processing systems","volume":"36","author":"Liu"},{"key":"ref49","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref50","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Alayrac"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref52","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2023"},{"key":"ref53","article-title":"Evaluation and mitigation of agnosia in multimodal large language models","author":"Lu","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref55","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref57","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801813.pdf?arnumber=10801813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:37:52Z","timestamp":1736883472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801813\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801813","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}