{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:52:02Z","timestamp":1774558322878,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tce.2026.3655466","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:54:49Z","timestamp":1768856089000},"page":"1156-1163","source":"Crossref","is-referenced-by-count":0,"title":["Manifold-Guided Geometric Enhancement for Reliable Multimodal Interaction in Consumer Electronics"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8919-0882","authenticated-orcid":false,"given":"XiaoYu","family":"Xu","sequence":"first","affiliation":[{"name":"Maynooth International Engineering College, Fuzhou University, Fuzhou, China"}]},{"given":"YuLan","family":"Pan","sequence":"additional","affiliation":[{"name":"Maynooth International Engineering College, Fuzhou University, Fuzhou, China"}]},{"given":"Xiaofeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Intelligent Wireless Network and Collaborative Control, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-3914","authenticated-orcid":false,"given":"Xuhang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Huizhou University, Huizhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8332-227X","authenticated-orcid":false,"given":"Kim-Fung","family":"Tsang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00147"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3412053"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3417688"},{"key":"ref7","article-title":"A survey on hallucination in large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv:2402.00253"},{"key":"ref8","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024","journal-title":"arXiv:2404.18930"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.322"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3378771"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref12","article-title":"Seeing clearly by layer two: Enhancing attention heads to alleviate hallucination in LVLMs","author":"Zhang","year":"2024","journal-title":"arXiv:2411.09968"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_8"},{"key":"ref14","article-title":"Devils in middle layers of large vision-language models: Interpreting, detecting and mitigating object hallucinations via attention lens","author":"Jiang","year":"2024","journal-title":"arXiv:2411.16724"},{"key":"ref15","article-title":"The hidden life of tokens: Reducing hallucination of large vision-language models via visual information steering","author":"Li","year":"2025","journal-title":"arXiv:2502.03628"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3460469"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2022.3232478"},{"key":"ref18","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref19","volume-title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","author":"Bronstein","year":"2021"},{"key":"ref20","first-page":"71102","article-title":"The geometry of hidden representations of large transformer models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Valeriani"},{"key":"ref21","first-page":"7694","article-title":"Hyperbolic image-text representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Desai"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02043-5"},{"key":"ref23","article-title":"Constrained belief updates explain geometric structures in transformer representations","author":"Li","year":"2025","journal-title":"arXiv:2502.01954"},{"key":"ref24","article-title":"Leveraging manifold embeddings for enhanced graph transformer representations and learning","author":"Wu","year":"2025","journal-title":"arXiv:2507.07335"},{"key":"ref25","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref28","article-title":"Reducing hallucinations in large vision-language models via latent space steering","volume-title":"Proc. The 13th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref29","article-title":"Look twice before you answer: Memory-space visual retracing for hallucination mitigation in multimodal large language models","author":"Zou","year":"2024","journal-title":"arXiv:2410.03577"},{"key":"ref30","article-title":"Mitigating object hallucination in large vision-language models via image-grounded guidance","author":"Zhao","year":"2024","journal-title":"arXiv:2402.08680"},{"key":"ref31","article-title":"Uncovering hidden geometry in transformers via disentangling position and context","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3708498"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3590908"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref39","article-title":"MM-vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv:2308.02490"},{"key":"ref40","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref42","article-title":"DoLa: Decoding by contrasting layers improves factuality in large language models","author":"Chuang","year":"2023","journal-title":"arXiv:2309.03883"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681076"},{"key":"ref44","article-title":"HALC: Object hallucination reduction via adaptive focal-contrast decoding","author":"Chen","year":"2024","journal-title":"arXiv:2403.00425"},{"key":"ref45","first-page":"92012","article-title":"Mitigating object hallucination via concentric causal attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Xing"},{"key":"ref46","article-title":"RITUAL: Random image transformations as a universal anti-hallucination lever in large vision language models","author":"Woo","year":"2024","journal-title":"arXiv:2405.17821"},{"key":"ref47","article-title":"Mitigating object hallucinations in large vision-language models with assembly of global and local attention","author":"An","year":"2024","journal-title":"arXiv:2406.12718"},{"key":"ref48","article-title":"Self-introspective decoding: Alleviating hallucinations for large vision-language models","author":"Huo","year":"2024","journal-title":"arXiv:2408.02032"},{"key":"ref49","article-title":"Intervening anchor token: Decoding strategy in alleviating hallucinations for MLLMs","volume-title":"Proc. The 13th Int. Conf. Learn. Represent.","author":"Tang"},{"key":"ref50","article-title":"See what you are told: Visual attention sink in large multimodal models","author":"Kang","year":"2025","journal-title":"arXiv:2503.03321"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11456295\/11358388.pdf?arnumber=11358388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:50:15Z","timestamp":1774554615000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11358388\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":50,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tce.2026.3655466","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}