{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T23:25:39Z","timestamp":1784762739250,"version":"3.55.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00918","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9845-9854","source":"Crossref","is-referenced-by-count":2,"title":["WalkVLM: Aid Visually Impaired People Walking by Vision Language Model"],"prefix":"10.1109","author":[{"given":"Zhiqiang","family":"Yuan","sequence":"first","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Zhang","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeshuang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiapei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Deng","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zexi","family":"Jia","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peixiang","family":"Luo","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyue","family":"Duan","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00232"},{"key":"ref3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"An introduction to vision-language modeling","author":"Bordes","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481291"},{"key":"ref6","article-title":"Llava-mole: Sparse mixture of lora experts for mitigating data conflicts in instruction finetuning mllms","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3656650.3656677"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref9","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3407191"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84628-867-8"},{"key":"ref13","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"A dataset for crucial object recognition in blind and low-vision individuals\u2019 navigation","author":"Touhidul Islam","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3688538"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3579496"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-025-00099-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC60209.2024.10463430"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref21","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref23","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00200"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref26","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Generating contextuallyrelevant navigation instructions for blind and low vision people","author":"Merchant","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"29","article-title":"Using tf-idf to determine word relevance in document queries","volume-title":"Proceedings of the first instructional conference on machine learning","author":"Ramos"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/s19153404"},{"key":"ref30","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Reid","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Mathllava: Bootstrapping mathematical reasoning for multimodal large language models","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-021-00837-9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2021.3096379"},{"key":"ref34","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Visiongpt: Llmassisted real-time anomaly detection for safe visual navigation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102486"},{"key":"ref39","article-title":"Emerging practices for large multimodal model (lmm) assistance for people with visual impairments: Implications for design","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/FMSys62467.2024.00010"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53654.2022.9945087"},{"key":"ref43","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Yi: Open foundation models by 01. ai","author":"Young","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122109"},{"key":"ref47","article-title":"Sparsevlm: Visual token sparsification for efficient vision-language model inference","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Vialm: A survey and benchmark of visually impaired assistance with large models","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3688863.3689575"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444414.pdf?arnumber=11444414","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:11Z","timestamp":1777611971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444414\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00918","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}