{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:52:59Z","timestamp":1782762779922,"version":"3.54.5"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"13","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271125"],"award-info":[{"award-number":["62271125"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019065","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2024YFG0003"],"award-info":[{"award-number":["2024YFG0003"]}],"id":[{"id":"10.13039\/501100019065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,7,1]]},"DOI":"10.1109\/jiot.2026.3686069","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:50:33Z","timestamp":1776801033000},"page":"28841-28850","source":"Crossref","is-referenced-by-count":0,"title":["Reliable Visual Perception and Reasoning via False Positive Detection and Correction"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7531-826X","authenticated-orcid":false,"given":"Ben","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lulu","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4834-9549","authenticated-orcid":false,"given":"Ke","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0709-6266","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6372-6843","authenticated-orcid":false,"given":"Chong","family":"Mu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9557-7739","authenticated-orcid":false,"given":"Hui","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"35438","article-title":"Internet of Things enabled indoor activity monitoring for visually impaired people with hybrid deep learning and optimized algorithms for enhanced safety","volume-title":"Sci. Rep.","volume":"15","author":"Al Duhayyim","year":"2025"},{"issue":"16","key":"ref2","doi-asserted-by":"crossref","first-page":"32701","DOI":"10.1109\/JIOT.2025.3579032","article-title":"Vision-language models for edge networks: A comprehensive survey","volume":"12","author":"Sharshar","year":"2025","journal-title":"IEEE Internet Things J."},{"issue":"7","key":"ref3","first-page":"6694","article-title":"Eve: Efficient multimodal vision language models with elastic visual experts","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"39","author":"Rang"},{"key":"ref4","article-title":"MiniCPM-V: A GPT-4 V level MLLM on your phone","author":"Yao","year":"2024","journal-title":"arXiv:2408.01800"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.632"},{"key":"ref6","article-title":"Improve mathematical reasoning in language models by automated process supervision","author":"Luo","year":"2024","journal-title":"arXiv:2406.06592"},{"key":"ref7","article-title":"Rewarding progress: Scaling automated process verifiers for LLM reasoning","author":"Setlur","year":"2024","journal-title":"arXiv:2410.08146"},{"key":"ref8","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Bosma","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref9","first-page":"7601","article-title":"ReFT: Reasoning with reinforced fine-tuning","volume-title":"Proc. 62nd Annu. Meeting Assoc. Comput. Linguistics (Volume 1: Long Papers)","author":"Trung"},{"key":"ref10","article-title":"Reason-RFT: Reinforcement fine-tuning for visual reasoning of vision language models","author":"Tan","year":"2025","journal-title":"arXiv:2503.20752"},{"issue":"2","key":"ref11","first-page":"1254","article-title":"Visual chain-of-thought prompting for knowledge-based visual reasoning","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"38","author":"Chen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3719341"},{"key":"ref13","first-page":"8612","article-title":"Visual CoT: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref14","first-page":"2087","article-title":"LLaVA-CoT: Let vision language models reason step-by-step","volume-title":"Proc. ICCV","author":"Xu"},{"key":"ref15","first-page":"2901","article-title":"CLEVR: A diagnostic dataset for compositional language and elementary visual reasoning","volume-title":"Proc. CVPR","author":"Johnson"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1016\/j.inffus.2022.11.011","article-title":"A review of emerging research directions in abstract visual reasoning","volume":"91","author":"Ma\u0142ki\u0144ski","year":"2022","journal-title":"Inf. Fusion"},{"key":"ref17","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref18","first-page":"42048","article-title":"MoME: Mixture of multimodal experts for generalist multimodal large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shen"},{"key":"ref19","first-page":"14205","article-title":"Omni-SMoLA: Boosting generalist multimodal models with soft mixture of low-rank experts","volume-title":"Proc. CVPR","author":"Wu"},{"key":"ref20","first-page":"32897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Aggarwal"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714892"},{"key":"ref22","first-page":"1857","article-title":"Self-bootstrapped visual-language model for knowledge selection and question answering","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Hao"},{"key":"ref23","article-title":"Multimodal reranking for knowledge-intensive visual question answering","author":"Wen","year":"2024","journal-title":"arXiv:2407.12277"},{"key":"ref24","article-title":"GeReA: Question-aware prompt captions for knowledge-based visual question answering","author":"Ma","year":"2024","journal-title":"arXiv:2402.02503"},{"key":"ref25","first-page":"67511","article-title":"GraphVis: Boosting LLMs with visual knowledge graph integration","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 37","author":"Deng"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591629"},{"key":"ref27","first-page":"6571","article-title":"MM-reasoner: A multi-modal knowledge-aware framework for knowledge-based visual question answering","volume-title":"Proc. Findings Assoc. Comput. Linguistics, EMNLP","author":"Khademi"},{"key":"ref28","first-page":"533","article-title":"Knowledge generation for zero-shot knowledge-based VQA","volume-title":"Proc. Findings Assoc. Comput. Linguistics, EACL","author":"Cao"},{"issue":"8","key":"ref29","doi-asserted-by":"crossref","first-page":"6797","DOI":"10.1109\/TPAMI.2025.3562422","article-title":"Prophet: Prompting large language models with complementary answer heuristics for knowledge-based visual question answering","volume":"47","author":"Yu","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref30","article-title":"Seeing is not reasoning: MVPBench for graph-based evaluation of multi-path visual physical CoT","author":"Dong","year":"2025","journal-title":"arXiv:2505.24182"},{"issue":"4","key":"ref31","doi-asserted-by":"crossref","first-page":"ep538","DOI":"10.30935\/cedtech\/15592","article-title":"Assessing AI\u2019s problem solving in physics: Analyzing reasoning, false positives and negatives through the force concept inventory","volume":"16","author":"Aldazharova","year":"2024","journal-title":"Contemp. Educ. Technol."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref33","first-page":"3195","article-title":"OK-VQA: A visual question answering benchmark requiring external knowledge","volume-title":"Proc. 6581","author":"Marino"},{"issue":"10","key":"ref34","doi-asserted-by":"crossref","first-page":"2413","DOI":"10.1109\/TPAMI.2017.2754246","article-title":"FVQA: Fact-based visual question answering","volume":"40","author":"Wang","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref35","article-title":"PromptCap: Prompt-guided task-aware image captioning","author":"Hu","year":"2022","journal-title":"arXiv:2211.09699"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_9"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11581326\/11489059.pdf?arnumber=11489059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:41:27Z","timestamp":1782762087000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11489059\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":36,"journal-issue":{"issue":"13"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2026.3686069","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,1]]}}}