{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T01:47:44Z","timestamp":1777945664197,"version":"3.51.4"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100007224","name":"NAFOSTED","doi-asserted-by":"publisher","award":["102.01-2024.23"],"award-info":[{"award-number":["102.01-2024.23"]}],"id":[{"id":"10.13039\/100007224","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.patrec.2026.03.017","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T16:43:23Z","timestamp":1773938603000},"page":"55-63","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Lightweight moment-residual-coherent patterns for image recognition"],"prefix":"10.1016","volume":"204","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5210-6152","authenticated-orcid":false,"given":"Thanh Tuan","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9621-9266","authenticated-orcid":false,"given":"Hoang Anh","family":"Pham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5646-8505","authenticated-orcid":false,"given":"Thanh Phuong","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5951-096X","authenticated-orcid":false,"given":"Thinh Vinh","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5290-2258","authenticated-orcid":false,"given":"Hoai Nam","family":"Vu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7554-1707","authenticated-orcid":false,"given":"Van-Dung","family":"Hoang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.patrec.2026.03.017_bib0001","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.patrec.2022.08.010","article-title":"Rotation invariant Gabor convolutional neural network for image classification","volume":"162","author":"Yao","year":"2022","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.017_bib0002","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.patrec.2023.01.003","article-title":"Image classification using graph neural network and multiscale wavelet superpixels","volume":"166","author":"Vasudevan","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.017_bib0003","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1016\/j.patrec.2021.01.015","article-title":"Adaptive hybrid attention network for hyperspectral image classification","volume":"144","author":"Pande","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.017_bib0004","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.patrec.2022.12.022","article-title":"Adaptive dynamic networks for object detection in aerial images","volume":"166","author":"Wu","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.017_bib0005","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.patrec.2022.06.006","article-title":"Transformer-based cross reference network for video salient object detection","volume":"160","author":"Huang","year":"2022","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.017_bib0006","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1016\/j.neucom.2022.06.052","article-title":"Residual attentive feature learning network for salient object detection","volume":"501","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.patrec.2026.03.017_bib0007","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s10044-024-01237-4","article-title":"LFFNet: lightweight feature-enhanced fusion network for real-time semantic segmentation of road scenes","volume":"27","author":"Hu","year":"2024","journal-title":"Pattern Anal. Appl."},{"key":"10.1016\/j.patrec.2026.03.017_bib0008","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.patrec.2023.07.010","article-title":"An ablation study on part-based face analysis using a multi-input convolutional neural network and semantic segmentation","volume":"173","author":"Abate","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.017_bib0009","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.patrec.2025.08.019","article-title":"A lightweight multi-scaled semantic segmentation for underground mine images","volume":"197","author":"Wang","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.017_bib0010","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.patrec.2017.03.016","article-title":"Evaluation of local descriptors and CNNs for non-adult detection in visual content","volume":"113","author":"Santana","year":"2018","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.017_bib0011","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/j.patrec.2020.04.031","article-title":"Real time human action recognition using triggered frame extraction and a typical CNN heuristic","volume":"135","author":"Mishra","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.017_bib0012","doi-asserted-by":"crossref","unstructured":"M.A.R. Ratul, M.H. Mozaffari, W.-S. Lee, E. Parimbelli, Skin lesions classification using deep learning based on dilated convolution, bioRxiv (2020).","DOI":"10.1101\/860700"},{"key":"10.1016\/j.patrec.2026.03.017_bib0013","unstructured":"A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam, MobileNets: efficient convolutional neural networks for mobile vision applications, CoRRabs\/1704.04861(2017)."},{"issue":"15","key":"10.1016\/j.patrec.2026.03.017_bib0014","first-page":"2937","article-title":"A lightweight and efficient deep convolutional neural network based on depthwise dilated separable convolution","volume":"98","author":"Nguyen","year":"2020","journal-title":"J. TAIT"},{"key":"10.1016\/j.patrec.2026.03.017_bib0015","series-title":"CVPR","first-page":"4510","article-title":"MobileNetV2: inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"10.1016\/j.patrec.2026.03.017_bib0016","first-page":"71","article-title":"DDCNNC: dilated and depthwise separable convolutional neural network for diagnosis COVID-19 via chest X-ray images","volume":"2","author":"Li","year":"2021","journal-title":"IJCCE"},{"issue":"4","key":"10.1016\/j.patrec.2026.03.017_bib0017","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s10994-024-06672-2","article-title":"NetTOP: a light-weight network of orthogonal-plane features for image recognition","volume":"114","author":"Nguyen","year":"2025","journal-title":"Mach. Learn."},{"key":"10.1016\/j.patrec.2026.03.017_bib0018","series-title":"DICTA","first-page":"265","article-title":"Assembling extra features with grouped pointwise convolutions for mobilenets","author":"Nguyen","year":"2023"},{"key":"10.1016\/j.patrec.2026.03.017_bib0019","first-page":"27","article-title":"A light-weight backbone to adapt with extracting grouped dilation features","volume":"28","author":"Nguyen","year":"2025","journal-title":"PAA"},{"key":"10.1016\/j.patrec.2026.03.017_bib0020","series-title":"ICCV","first-page":"1314","article-title":"Searching for MobileNetV3","author":"Howard","year":"2019"},{"key":"10.1016\/j.patrec.2026.03.017_bib0021","series-title":"CVPR","first-page":"6848","article-title":"ShuffleNet: an extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2018"},{"key":"10.1016\/j.patrec.2026.03.017_bib0022","series-title":"ECCV","first-page":"122","article-title":"ShuffleNet V2: practical guidelines for efficient CNN architecture design","volume":"11218","author":"Ma","year":"2018"},{"key":"10.1016\/j.patrec.2026.03.017_bib0023","series-title":"CVPR","first-page":"1800","article-title":"Xception: deep learning with depthwise separable convolutions","author":"Chollet","year":"2017"},{"key":"10.1016\/j.patrec.2026.03.017_bib0024","series-title":"CVPR","first-page":"2820","article-title":"MnasNet: platform-aware neural architecture search for mobile","author":"Tan","year":"2019"},{"key":"10.1016\/j.patrec.2026.03.017_bib0025","series-title":"ICML","first-page":"6105","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","volume":"97","author":"Tan","year":"2019"},{"key":"10.1016\/j.patrec.2026.03.017_bib0026","series-title":"NeurIPS","article-title":"GhostNetV2: enhance cheap operation with long-Range attention","author":"Tang","year":"2022"},{"key":"10.1016\/j.patrec.2026.03.017_bib0027","series-title":"ECCV","first-page":"680","article-title":"Rethinking bottleneck structure for efficient mobile network design","author":"Zhou","year":"2020"},{"key":"10.1016\/j.patrec.2026.03.017_bib0028","series-title":"SCOReD","first-page":"333","article-title":"Spatial pyramid pooling with atrous convolutional for MobileNet","author":"Mohamed","year":"2020"},{"key":"10.1016\/j.patrec.2026.03.017_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127942","article-title":"Efficient tick-shape networks of full-residual point-depth-point blocks for image classification","volume":"596","author":"Nguyen","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patrec.2026.03.017_bib0030","series-title":"ISCIT","article-title":"Transitional patterns for tick-shape backbones","author":"Le","year":"2025"},{"key":"10.1016\/j.patrec.2026.03.017_bib0031","series-title":"MIWAI","first-page":"116","article-title":"Spread-learned spatial features to improve tick-Shape networks","volume":"16353","author":"Hoang","year":"2025"},{"issue":"8","key":"10.1016\/j.patrec.2026.03.017_bib0032","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0271225","article-title":"A lightweight deep neural network with higher accuracy","volume":"17","author":"Zhao","year":"2022","journal-title":"PLoS One"},{"key":"10.1016\/j.patrec.2026.03.017_bib0033","series-title":"CVPR","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.patrec.2026.03.017_bib0034","unstructured":"A. Krizhevsky, G. Hinton, Learning multiple layers of features from tiny images, Tech Report, 2009."},{"key":"10.1016\/j.patrec.2026.03.017_bib0035","series-title":"CVPR","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.patrec.2026.03.017_bib0036","series-title":"BMVC","article-title":"Wide residual networks","author":"Zagoruyko","year":"2016"},{"key":"10.1016\/j.patrec.2026.03.017_bib0037","series-title":"CVPR","first-page":"14588","article-title":"Rethinking depthwise separable convolutions: how intra-kernel correlations lead to improved mobilenets","author":"Haase","year":"2020"},{"key":"10.1016\/j.patrec.2026.03.017_bib0038","series-title":"CVPR","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.patrec.2026.03.017_bib0039","series-title":"BMVC","first-page":"147","article-title":"BAM: bottleneck attention module","author":"Park","year":"2018"},{"key":"10.1016\/j.patrec.2026.03.017_bib0040","series-title":"ECCV","first-page":"3","article-title":"CBAM: convolutional block attention module","volume":"11211","author":"Woo","year":"2018"},{"key":"10.1016\/j.patrec.2026.03.017_bib0041","series-title":"ECCV","first-page":"776","article-title":"Contrastive multiview coding","volume":"12356","author":"Tian","year":"2020"},{"key":"10.1016\/j.patrec.2026.03.017_bib0042","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.patrec.2024.07.001","article-title":"Rescaling large datasets based on validation outcomes of a pre-trained network","volume":"185","author":"Nguyen","year":"2024","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.017_bib0043","series-title":"CVPR Workshop","article-title":"Novel dataset for fine-grained image categorization","author":"Khosla","year":"2011"},{"key":"10.1016\/j.patrec.2026.03.017_bib0044","series-title":"NeurIPS","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"issue":"6","key":"10.1016\/j.patrec.2026.03.017_bib0045","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","article-title":"Places: a 10 million image database for scene recognition","volume":"40","author":"Zhou","year":"2018","journal-title":"PAMI"},{"key":"10.1016\/j.patrec.2026.03.017_bib0046","unstructured":"V. Sovrasov, ptflops: a flops counting tool for neural networks in pytorch framework, 2018\u20132024, (????)."},{"issue":"9","key":"10.1016\/j.patrec.2026.03.017_bib0047","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"10.1016\/j.patrec.2026.03.017_bib0048","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE PAMI"},{"key":"10.1016\/j.patrec.2026.03.017_bib0049","series-title":"MAPR","first-page":"1","article-title":"Enhanced mobilenets via augmentation of filtering-based features","author":"Tran","year":"2025"},{"key":"10.1016\/j.patrec.2026.03.017_bib0050","unstructured":"L. Ye, AugShuffleNet: communicate more, compute less, CoRRabs\/2203.06589(2022)."},{"key":"10.1016\/j.patrec.2026.03.017_bib0051","unstructured":"F.N. Iandola, M.W. Moskewicz, K. Ashraf, S. Han, W.J. Dally, K. Keutzer, SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size, CoRR abs\/1602.07360(2016)."},{"key":"10.1016\/j.patrec.2026.03.017_bib0052","series-title":"CVPR","first-page":"2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"10.1016\/j.patrec.2026.03.017_bib0053","series-title":"CVPR","article-title":"MobileOne: an improved one millisecond mobile backbone","author":"Vasu","year":"2023"},{"issue":"4","key":"10.1016\/j.patrec.2026.03.017_bib0054","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/s10044-024-01327-3","article-title":"ShuffleNeMt: modern lightweight convolutional neural network architecture","volume":"27","author":"Zhu","year":"2024","journal-title":"Pattern Anal. Appl."},{"key":"10.1016\/j.patrec.2026.03.017_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128018","article-title":"MirageNet: improving the network performance of image understanding with very low FLOPs","volume":"286","author":"Fu","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patrec.2026.03.017_bib0056","doi-asserted-by":"crossref","first-page":"8251","DOI":"10.1109\/TMM.2025.3604954","article-title":"SLCGC: a lightweight self-supervised low-pass contrastive graph clustering network for hyperspectral images","volume":"27","author":"Ding","year":"2025","journal-title":"IEEE Trans. Multim."},{"key":"10.1016\/j.patrec.2026.03.017_bib0057","first-page":"1","article-title":"Adaptive homophily clustering: structure homophily graph learning with adaptive filter for hyperspectral image","volume":"63","author":"Ding","year":"2025","journal-title":"IEEE TGRS"},{"issue":"2","key":"10.1016\/j.patrec.2026.03.017_bib0058","doi-asserted-by":"crossref","DOI":"10.1007\/s10044-025-01429-6","article-title":"Accumulating global channel-wise patterns via deformed-bottleneck recalibration for image classification","volume":"28","author":"Nguyen","year":"2025","journal-title":"Pattern Anal. Appl."}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526001078?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526001078?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T12:39:59Z","timestamp":1777725599000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865526001078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":58,"alternative-id":["S0167865526001078"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.03.017","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Lightweight moment-residual-coherent patterns for image recognition","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.03.017","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}