{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T23:17:29Z","timestamp":1784589449746,"version":"3.55.0"},"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T00:00:00Z","timestamp":1771286400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Open-world object detection (OWOD) has become a crucial paradigm for advancing intelligent perception systems, as it requires not only accurate recognition of known categories but also autonomous discovery and continuous learning of emerging unknown categories in dynamic environments. However, existing methods often suffer from shallow cross-modal interaction and rigid reasoning mechanisms, making them unable to cope with the continuous emergence of new categories and the dynamic changes in modality reliability in open-world environments. First, to achieve hypergraph enhancement, image regions, text, and semantic prototypes are treated as nodes, while a gating network dynamically generates hyperedges under semantic and spatial constraints, thereby modeling the high-order dependencies of vision\u2013language\u2013semantic triplets and enabling deep multimodal fusion at the topological level. Second, a hierarchical hypergraph convolutional network is designed to facilitate knowledge propagation between known and unknown categories. Finally, a meta-policy gradient-based adaptive controller is proposed, which dynamically adjusts feature fusion weights, propagation depth, and attention topology based on the detection state and historical trajectories. Experimental results on the OWOD dataset show that our proposed method achieves an accuracy of 76.8%, providing a new paradigm for open-world multimodal perception that integrates semantic depth and adaptability.<\/jats:p>","DOI":"10.1371\/journal.pone.0342169","type":"journal-article","created":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T18:34:23Z","timestamp":1771353263000},"page":"e0342169","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Hyper-MDR: An open-world multimodal reasoning framework based on dynamic hypergraph and meta-strategy optimization"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1967-3691","authenticated-orcid":true,"given":"Jian","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianhai","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"key":"pone.0342169.ref001","doi-asserted-by":"crossref","first-page":"103812","DOI":"10.1016\/j.dsp.2022.103812","article-title":"A comprehensive review of object detection with deep learning","volume":"132","author":"R Kaur","year":"2023","journal-title":"Digit Signal Process"},{"issue":"9","key":"pone.0342169.ref002","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-025-11284-w","article-title":"Comprehensive review of recent developments in visual object detection based on deep learning","volume":"58","author":"E Edozie","year":"2025","journal-title":"Artif Intell Rev"},{"issue":"9","key":"pone.0342169.ref003","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-024-10877-1","article-title":"A comprehensive survey of deep learning-based lightweight object detection models for edge devices","volume":"57","author":"P Mittal","year":"2024","journal-title":"Artif Intell Rev"},{"key":"pone.0342169.ref004","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.neucom.2023.01.056","article-title":"A systematic review and analysis of deep learning-based underwater object detection","volume":"527","author":"S Xu","year":"2023","journal-title":"Neurocomputing"},{"key":"pone.0342169.ref005","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1117\/12.3049936","article-title":"A survey of object detection based on deep learning","volume-title":"Fourth International Conference on Advanced Algorithms and Neural Networks (AANN 2024)","author":"W Jiang","year":"2024"},{"issue":"8","key":"pone.0342169.ref006","doi-asserted-by":"crossref","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: a survey","volume":"46","author":"J Zhang","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"pone.0342169.ref007","article-title":"A survey on efficient vision\u2010language models","volume":"15","author":"G Shinde","year":"2025","journal-title":"Wiley Interdiscip Rev: Data Mining Knowl Discov"},{"key":"pone.0342169.ref008","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.procs.2025.08.008","article-title":"Open-vocabulary object detection survey","volume":"266","author":"X Yu","year":"2025","journal-title":"Procedia Comput Sci"},{"issue":"12","key":"pone.0342169.ref009","doi-asserted-by":"crossref","first-page":"3668","DOI":"10.3390\/s25123668","article-title":"A survey of deep learning-driven 3D object detection: sensor modalities, technical architectures, and applications","volume":"25","author":"X Zhang","year":"2025","journal-title":"Sensors (Basel)"},{"issue":"5","key":"pone.0342169.ref010","article-title":"RGB-LiDAR fusion for accurate 2D and 3D object detection","volume":"34","author":"M Mousa-Pasandi","year":"2023","journal-title":"Machi Vis Appl"},{"key":"pone.0342169.ref011","first-page":"920","article-title":"Towards Robust Perception for Assistive Robotics: An RGB-Event-LiDAR Dataset and Multi-Modal Detection Pipeline","volume-title":"2024 IEEE 20th International Conference on Automation Science and Engineering (CASE","author":"A Scicluna","year":"2024"},{"key":"pone.0342169.ref012","article-title":"R-livit: A lidar-visual-thermal dataset enabling vulnerable road user focused roadside perception","author":"J Mirlach","year":"2025","journal-title":"arXiv preprint"},{"key":"pone.0342169.ref013","first-page":"20158","article-title":"DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition.","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"C Li","year":"2025"},{"key":"pone.0342169.ref014","article-title":"Softhgnn: Soft hypergraph neural networks for general visual recognition","author":"M Lei","year":"2025","journal-title":"arXiv preprint arXiv:2505.15325"},{"key":"pone.0342169.ref015","article-title":"Hyper-yolo: When visual object detection meets hypergraph computation","author":"Y Feng","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"23","key":"pone.0342169.ref016","article-title":"Joint object detection and multi-object tracking based on hypergraph matching","volume":"14","author":"Z Cui","year":"2024","journal-title":"Appl Sci"},{"key":"pone.0342169.ref017","first-page":"1","article-title":"Hypergraph-based asynchronous event processing for moving object classification","author":"N Yu","year":"2024","journal-title":"J Shanghai Jiaotong Univ (Science)"},{"issue":"8","key":"pone.0342169.ref018","doi-asserted-by":"crossref","first-page":"3526","DOI":"10.3390\/app14083526","article-title":"Hypergraph position attention convolution networks for 3d point cloud segmentation","volume":"14","author":"Y Rong","year":"2024","journal-title":"Appl Sci"},{"key":"pone.0342169.ref019","first-page":"5830","article-title":"Towards open world object detection.","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"KJ Joseph","year":"2021"},{"key":"pone.0342169.ref020","first-page":"193","article-title":"UC-OWOD: Unknown-classified open world object detection","volume-title":"European Conference on Computer Vision","author":"Z Wu","year":"2022"},{"key":"pone.0342169.ref021","first-page":"11444","article-title":"Prob: Probabilistic objectness for open world object detection","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"O Zohar","year":"2023"},{"key":"pone.0342169.ref022","doi-asserted-by":"crossref","first-page":"8207","DOI":"10.1109\/WACV61041.2025.00796","article-title":"Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection","volume-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","author":"R Inoue","year":"2025"},{"key":"pone.0342169.ref023","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"X Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"pone.0342169.ref024","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3225438","article-title":"Hyperspectral image classification using feature fusion hypergraph convolution neural network","volume":"60","author":"Z Ma","year":"2022","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0342169.ref025","first-page":"350","article-title":"Detecting twenty-thousand classes using image-level supervision","volume-title":"European Conference on Computer Vision","author":"X Zhou","year":"2022"},{"key":"pone.0342169.ref026","first-page":"106","article-title":"Open-vocabulary detr with conditional matching","volume-title":"European Conference on Computer Vision","author":"Y Zang","year":"2022"},{"key":"pone.0342169.ref027","first-page":"10965","article-title":"Grounded language-image pre-training","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L H Li","year":"2022"},{"key":"pone.0342169.ref028","first-page":"1780","article-title":"Mdetr-modulated detection for end-to-end multi-modal understanding","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"A Kamath","year":"2021"},{"key":"pone.0342169.ref029","doi-asserted-by":"crossref","first-page":"112539","DOI":"10.1016\/j.knosys.2024.112539","article-title":"Multi-view distillation based on multi-modal fusion for few-shot action recognition (CLIP-MDMF)","volume":"304","author":"F Guo","year":"2024","journal-title":"Knowl-Based Syst"},{"key":"pone.0342169.ref030","doi-asserted-by":"crossref","first-page":"8062","DOI":"10.1145\/3664647.3681275","article-title":"Multimodal Inplace Prompt Tuning for Open-set Object Detection","volume-title":"Proceedings of the 32nd ACM International Conference on Multimedia","author":"G Li","year":"2024"},{"key":"pone.0342169.ref031","first-page":"5252","article-title":"Mt-detr: Robust end-to-end multimodal detection with confidence fusion","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"SY Chu","year":"2023"},{"key":"pone.0342169.ref032","doi-asserted-by":"crossref","first-page":"5730","DOI":"10.1109\/WACV61041.2025.00559","article-title":"Cross-Aligned Fusion For Multimodal Understanding","volume-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","author":"A Rajora","year":"2025"},{"key":"pone.0342169.ref033","doi-asserted-by":"crossref","first-page":"106362","DOI":"10.1016\/j.ymssp.2019.106362","article-title":"Theoretical characterization and modal directivity investigation of the interaction noise for a small contra-rotating fan","volume":"135","author":"B Dong","year":"2020","journal-title":"Mech Syst Signal Process"},{"key":"pone.0342169.ref034","doi-asserted-by":"crossref","first-page":"108861","DOI":"10.1016\/j.compbiomed.2024.108861","article-title":"Enhanced tissue slide imaging in the complex domain via cross-explainable GAN for Fourier ptychographic microscopy","volume":"179","author":"F Bardozzo","year":"2024","journal-title":"Comput Biol Med"},{"issue":"2","key":"pone.0342169.ref035","doi-asserted-by":"crossref","first-page":"138","DOI":"10.26599\/JICV.2023.9210036","article-title":"Kinematics-aware multigraph attention network with residual learning for heterogeneous trajectory prediction","volume":"7","author":"Z Sheng","year":"2024","journal-title":"J Int Con Veh"},{"issue":"10","key":"pone.0342169.ref036","doi-asserted-by":"crossref","first-page":"17654","DOI":"10.1109\/TITS.2022.3155749","article-title":"Graph-based spatial-temporal convolutional network for vehicle trajectory prediction in autonomous driving","volume":"23","author":"Z Sheng","year":"2022","journal-title":"IEEE Trans Intell Transport Syst"},{"key":"pone.0342169.ref037","first-page":"1923","volume-title":"Hypergraph Structure Learning for Hypergraph Neural Networks","author":"D Cai","year":"2022"},{"key":"pone.0342169.ref038","article-title":"Hypergraph dynamic system","volume-title":"The Twelfth International Conference on Learning Representations","author":"J Yan","year":"2024"},{"key":"pone.0342169.ref039","first-page":"25454","article-title":"OW-OVD: Unified Open World and Open Vocabulary Object Detection","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"X Xi","year":"2025"},{"key":"pone.0342169.ref040","first-page":"68190","article-title":"OW-VAP: Visual Attribute Parsing for Open World Object Detection.","volume-title":"International Conference on Machine Learning","author":"X Xi","year":"2025"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0342169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T18:34:30Z","timestamp":1771353270000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0342169"}},"subtitle":[],"editor":[{"given":"Francesco","family":"Bardozzo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,2,17]]},"references-count":40,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2,17]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0342169","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,17]]}}}