{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T11:16:58Z","timestamp":1772795818237,"version":"3.50.1"},"reference-count":32,"publisher":"World Scientific Pub Co Pte Ltd","issue":"05","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:p>Multispectral image analysis plays a pivotal role in remote sensing, precision agriculture, and environmental monitoring. However, the diverse spatial and spectral characteristics of multispectral data pose significant challenges for robust feature extraction and accurate recognition. In this work, we propose Optimization-Driven Multi-Scale Attention Fusion (ODMAF), a novel framework that integrates multi-scale convolutional feature extraction with an optimization-driven attention fusion mechanism. ODMAF first generates a hierarchy of spatial\u2013spectral features via parallel multi-scale convolutional branches and spectral attention modules. These features are then adaptively fused through a mathematically principled attention mechanism, formulated as a constrained optimization problem with entropy regularization to encourage diversity and interpretability. Unlike prior attention-based methods, ODMAF frames attention weight learning as a constrained, entropy-regularized optimization problem with theoretical guarantees on optimality and generalization, and explicitly unifies spatial and spectral feature hierarchies for interpretable fusion. Comprehensive experiments on four benchmark hyperspectral datasets demonstrate that ODMAF achieves state-of-the-art performance, improving overall accuracy by 1.5\u20132.3% over the best-performing baselines (e.g. achieving 97.7% OA on Indian Pines and 99.8% on Pavia University) and surpassing several competitive deep learning baselines in terms of overall accuracy, convergence stability, and model interpretability. Visualization and theoretical analysis further verify that ODMAF effectively captures class-specific, multi-scale feature contributions, providing a robust and transparent solution for multispectral image understanding. Beyond benchmark accuracy, ODMAF\u2019s optimization-driven fusion is efficient and scalable, enabling practical deployment in operational remote sensing, agriculture monitoring, and large-scale environmental analytics.<\/jats:p>","DOI":"10.1142\/s0218001425500454","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:57:52Z","timestamp":1765346272000},"source":"Crossref","is-referenced-by-count":0,"title":["ODMAF: Optimization-Driven Multi-Scale Attention Fusion for Multispectral Image Feature Extraction and Recognition"],"prefix":"10.1142","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1163-5986","authenticated-orcid":false,"given":"Linsui","family":"Li","sequence":"first","affiliation":[{"name":"Guangxi Power Grid Co., Ltd., Nanning, Guangxi 530022, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7236-1280","authenticated-orcid":false,"given":"Zipei","family":"Guo","sequence":"additional","affiliation":[{"name":"Qinzhou Power Supply Bureau of Guangxi Power Grid Co., Ltd., Qinzhou, Guangxi 535000, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4648-8283","authenticated-orcid":false,"given":"Zhengpeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Guangxi Power Grid Co., Ltd., Nanning, Guangxi 530022, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0945-0311","authenticated-orcid":false,"given":"Pengfei","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangxi Power Grid Co., Ltd., Nanning, Guangxi 530022, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8512-0485","authenticated-orcid":false,"given":"Han","family":"Xu","sequence":"additional","affiliation":[{"name":"Fangchenggang Power Supply Bureau of Guangxi Power Grid Co., Ltd., Fangchenggang, Guangxi 538001, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"S0218001425500454BIB001","unstructured":"AVIRIS Sensor\/Purdue University, Salinas scene hyperspectral dataset (1998), 512\u00d7217 pixels, 204 usable spectral bands."},{"key":"S0218001425500454BIB002","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3552783"},{"key":"S0218001425500454BIB003","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-024-01515-y"},{"key":"S0218001425500454BIB004","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2015.2388577"},{"key":"S0218001425500454BIB005","unstructured":"D. Cozzolino, G. Poggi and L. Verdoliva, Pavia center dataset, ROSIS Sensor Data (2002), 1096\u00d71096 pixels, 102 spectral bands."},{"key":"S0218001425500454BIB006","unstructured":"D. Cozzolino, G. Poggi and L. Verdoliva, Pavia university dataset, ROSIS Sensor Data (2002), 610\u00d7340 pixels, 103 spectral bands."},{"key":"S0218001425500454BIB007","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2025.3583947"},{"key":"S0218001425500454BIB008","first-page":"1","volume":"61","author":"Guan R.","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"S0218001425500454BIB009","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3412417"},{"key":"S0218001425500454BIB010","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3338978"},{"key":"S0218001425500454BIB011","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3501412"},{"key":"S0218001425500454BIB012","doi-asserted-by":"publisher","DOI":"10.3390\/rs15071758"},{"key":"S0218001425500454BIB013","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2025.3587617"},{"key":"S0218001425500454BIB014","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3521195"},{"key":"S0218001425500454BIB015","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113392"},{"key":"S0218001425500454BIB016","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3571210"},{"key":"S0218001425500454BIB017","unstructured":"Purdue University, Indian pines hyperspectral dataset (1992), AVIRIS dataset, 145\u00d7145 pixels, 220 bands."},{"key":"S0218001425500454BIB018","doi-asserted-by":"publisher","DOI":"10.3390\/rs13030335"},{"key":"S0218001425500454BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2918719"},{"key":"S0218001425500454BIB020","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3417690"},{"key":"S0218001425500454BIB021","doi-asserted-by":"publisher","DOI":"10.3390\/rs16122185"},{"key":"S0218001425500454BIB022","doi-asserted-by":"publisher","DOI":"10.3390\/rs15081978"},{"key":"S0218001425500454BIB023","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3145917"},{"key":"S0218001425500454BIB024","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13020262"},{"key":"S0218001425500454BIB025","doi-asserted-by":"publisher","DOI":"10.3390\/rs15041151"},{"key":"S0218001425500454BIB026","doi-asserted-by":"publisher","DOI":"10.3390\/rs17071118"},{"key":"S0218001425500454BIB027","first-page":"1","volume":"61","author":"Xu F.","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"S0218001425500454BIB028","first-page":"1","volume":"60","author":"Yu H.","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"S0218001425500454BIB029","doi-asserted-by":"publisher","DOI":"10.3390\/rs15215238"},{"key":"S0218001425500454BIB030","doi-asserted-by":"publisher","DOI":"10.3390\/rs16122051"},{"key":"S0218001425500454BIB031","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106017"},{"key":"S0218001425500454BIB032","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2755542"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001425500454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T09:23:07Z","timestamp":1772788987000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218001425500454"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,13]]},"references-count":32,"journal-issue":{"issue":"05","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1142\/S0218001425500454"],"URL":"https:\/\/doi.org\/10.1142\/s0218001425500454","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"value":"0218-0014","type":"print"},{"value":"1793-6381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,13]]},"article-number":"2550045"}}