{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:04:09Z","timestamp":1784531049127,"version":"3.55.0"},"reference-count":64,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.imavis.2026.106050","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T15:53:29Z","timestamp":1780070009000},"page":"106050","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Semantic-preserving augmentation with saliency-aware geometric fusion for long-tailed visual recognition"],"prefix":"10.1016","volume":"173","author":[{"given":"Wu","family":"Zeng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6547-4424","authenticated-orcid":false,"given":"Mei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhili","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guojun","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"25","key":"10.1016\/j.imavis.2026.106050_b1","first-page":"01","article-title":"Advancements in computer vision: Bridging perception and intelligence","volume":"7","author":"Aggarwal","year":"2025","journal-title":"Acta Sci. Comput. Sci."},{"key":"10.1016\/j.imavis.2026.106050_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2022.105350","article-title":"COVID-19 image classification using deep learning: Advances, challenges and opportunities","volume":"144","author":"Aggarwal","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.imavis.2026.106050_b3","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1186\/s12880-022-00793-7","article-title":"Transfer learning for medical image classification: A literature review","volume":"22","author":"Kim","year":"2022","journal-title":"BMC Med. Imaging"},{"issue":"12","key":"10.1016\/j.imavis.2026.106050_b4","doi-asserted-by":"crossref","first-page":"7142","DOI":"10.3934\/era.2023362","article-title":"A survey of generative adversarial networks and their application in text-to-image synthesis","volume":"31","author":"Zeng","year":"2023","journal-title":"Electron. Res. Arch."},{"issue":"6","key":"10.1016\/j.imavis.2026.106050_b5","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/MSP.2017.2741510","article-title":"Deep learning for image-to-text generation: A technical overview","volume":"34","author":"He","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"10.1016\/j.imavis.2026.106050_b6","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":"Xu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.imavis.2026.106050_b7","doi-asserted-by":"crossref","first-page":"9243","DOI":"10.1007\/s11042-022-13644-y","article-title":"Object detection using YOLO: Challenges, architectural successors, datasets and applications","volume":"82","author":"Diwan","year":"2023","journal-title":"Multimedia Tools Appl."},{"issue":"4","key":"10.1016\/j.imavis.2026.106050_b8","doi-asserted-by":"crossref","first-page":"2674","DOI":"10.3934\/era.2026124","article-title":"Deep learning-based object detection: A comprehensive review of YOLO, RCNN, and SSD series","volume":"34","author":"Zeng","year":"2026","journal-title":"Electron. Res. Arch."},{"key":"10.1016\/j.imavis.2026.106050_b9","doi-asserted-by":"crossref","unstructured":"R. Thukral, A.S. Arora, A.K. Aggarwal, et al., Effectiveness of passive thermography in predicting mucositis in head and neck cancer patients using light-weight convolutional neural networks approach, in: International Conference on Frontiers of Intelligent Computing: Theory and Applications, 2024, pp. 1\u201313.","DOI":"10.1007\/978-981-96-2124-8_1"},{"key":"10.1016\/j.imavis.2026.106050_b10","series-title":"Modeling and Optimization of Signals Using Machine Learning Techniques","first-page":"327","article-title":"Current advancements in steganography: a review","author":"Garg","year":"2024"},{"key":"10.1016\/j.imavis.2026.106050_b11","series-title":"Second Int. Conf. Innov. Trends Electron. Eng.","first-page":"83","article-title":"Biometric system security issues and challenges.","author":"Chopra","year":"2016"},{"key":"10.1016\/j.imavis.2026.106050_b12","first-page":"679","article-title":"Few-shot learning based on deep learning: A survey","author":"Zeng","year":"2024","journal-title":"Math. Biosci. Eng."},{"key":"10.1016\/j.imavis.2026.106050_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.113563","article-title":"Leveraging multi-strategy labels for long-tailed classification","volume":"166","author":"Zeng","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.imavis.2026.106050_b14","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1186\/s13023-020-01374-z","article-title":"Diagnosis support systems for rare diseases: a scoping review","volume":"15","author":"Faviez","year":"2020","journal-title":"Orphanet J. Rare Dis."},{"key":"10.1016\/j.imavis.2026.106050_b15","doi-asserted-by":"crossref","first-page":"7157","DOI":"10.1007\/s11760-024-03382-z","article-title":"Improving long-tailed classification with PixDyMix: a localized pixel-level mixing method","author":"Zeng","year":"2024","journal-title":"Signal, Image Video Process."},{"key":"10.1016\/j.imavis.2026.106050_b16","doi-asserted-by":"crossref","unstructured":"S. Park, Y. Hong, B. Heo, et al., The majority can help the minority: Context-rich minority oversampling for long-tailed classification, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 6877\u20136886.","DOI":"10.1109\/CVPR52688.2022.00676"},{"key":"10.1016\/j.imavis.2026.106050_b17","first-page":"31","article-title":"Enhancing long-tailed classification via multi-strategy weighted experts with hybrid distillation","volume":"38","author":"Zeng","year":"2025","journal-title":"Multimedia Syst."},{"key":"10.1016\/j.imavis.2026.106050_b18","doi-asserted-by":"crossref","unstructured":"H. Chou, S.C. Chang, J.Y. Pan, Remix: rebalanced mixup, in: Computer Vision\u2013ECCV 2020 Workshops, 2020, pp. 95\u2013110.","DOI":"10.1007\/978-3-030-65414-6_9"},{"key":"10.1016\/j.imavis.2026.106050_b19","series-title":"Mixup: Beyond empirical risk minimization","author":"Zhang","year":"2017"},{"key":"10.1016\/j.imavis.2026.106050_b20","doi-asserted-by":"crossref","unstructured":"S. Yun, D. Han, S.J. Oh, et al., CutMix: Regularization strategy to train strong classifiers with localizable features, in: 2019 IEEE\/CVF International Conference on Computer Vision, ICCV, 2019, pp. 6022\u20136031.","DOI":"10.1109\/ICCV.2019.00612"},{"key":"10.1016\/j.imavis.2026.106050_b21","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.imavis.2026.106050_b22","doi-asserted-by":"crossref","unstructured":"H. Han, W.Y. Wang, B.H. Mao, Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning, in: 2005 International Conference on Intelligent Computing, 2005, pp. 878\u2013887.","DOI":"10.1007\/11538059_91"},{"key":"10.1016\/j.imavis.2026.106050_b23","doi-asserted-by":"crossref","unstructured":"C. Bunkhumpornpat, K. Sinapiromsaran, C. Lursinsap, Safe-level-smote: Safe-level-synthetic minority over-sampling technique for handling the class imbalanced problem, in: Advances in Knowledge Discovery and Data Mining: 13th Pacific-Asia Conference, 2009, pp. 475\u2013482.","DOI":"10.1007\/978-3-642-01307-2_43"},{"key":"10.1016\/j.imavis.2026.106050_b24","doi-asserted-by":"crossref","unstructured":"Y. Cui, M. Jia, T.Y. Lin, et al., Class-balanced loss based on effective number of samples, in: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019, pp. 9268\u20139277.","DOI":"10.1109\/CVPR.2019.00949"},{"key":"10.1016\/j.imavis.2026.106050_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105307","article-title":"MinoritySalMix and adaptive semantic weight compensation for long-tailed classification","volume":"152","author":"Zeng","year":"2024","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106050_b26","doi-asserted-by":"crossref","first-page":"4215","DOI":"10.1109\/TIP.2024.3425148","article-title":"Enhanced long-tailed recognition with contrastive CutMix augmentation","volume":"33","author":"Pan","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.imavis.2026.106050_b27","doi-asserted-by":"crossref","unstructured":"M.K. Li, Z.K. Hu, Y. Lu, et al., Feature fusion from head to tail for long-tailed visual recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, AAAI, 2024, pp. 13581\u201313589.","DOI":"10.1609\/aaai.v38i12.29262"},{"key":"10.1016\/j.imavis.2026.106050_b28","first-page":"32","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","author":"Cao","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106050_b29","first-page":"4175","article-title":"Balanced meta-softmax for long-tailed visual recognition","author":"Ren","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106050_b30","first-page":"32","article-title":"Meta-weight-net: learning an explicit mapping for sample weighting","author":"Shu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106050_b31","doi-asserted-by":"crossref","unstructured":"J.G. Zhu, Z. Wang, J.J. Chen, et al., Balanced contrastive learning for long-tailed visual recognition, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 6898\u20136907.","DOI":"10.1109\/CVPR52688.2022.00678"},{"key":"10.1016\/j.imavis.2026.106050_b32","doi-asserted-by":"crossref","first-page":"6190","DOI":"10.3934\/mbe.2024272","article-title":"Image data augmentation techniques based on deep learning: A survey","author":"Zeng","year":"2024","journal-title":"Math. Biosci. Eng."},{"key":"10.1016\/j.imavis.2026.106050_b33","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1007\/s11760-024-03706-z","article-title":"A low-light image enhancement network based on multi-layer feature aggregation and multi-branch attention mechanisms","volume":"19","author":"Zeng","year":"2025","journal-title":"SIViP"},{"key":"10.1016\/j.imavis.2026.106050_b34","series-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"10.1016\/j.imavis.2026.106050_b35","series-title":"Saliencymix: A saliency guided data augmentation strategy for better regularization","author":"Uddin","year":"2020"},{"key":"10.1016\/j.imavis.2026.106050_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.130886","article-title":"DualAttendMed: A coarse-to-fine dual-stage attention framework for interpretable disease localization and classification","volume":"305","author":"Abbas","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.imavis.2026.106050_b37","doi-asserted-by":"crossref","unstructured":"X. Hou, L. Zhang, Saliency detection: A spectral residual approach, in: 2007 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2007, pp. 1\u20138.","DOI":"10.1109\/CVPR.2007.383267"},{"key":"10.1016\/j.imavis.2026.106050_b38","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/j.imavis.2009.06.006","article-title":"Human detection using a mobile platform and novel features derived from a visual saliency mechanism","author":"Montabone","year":"2010","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106050_b39","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.imavis.2026.106050_b40","doi-asserted-by":"crossref","unstructured":"Z. Liu, Z. Miao, X. Zhan, J. Wang, et al., Large-scale long-tailed recognition in an open world, in: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019, pp. 2532\u20132541.","DOI":"10.1109\/CVPR.2019.00264"},{"key":"10.1016\/j.imavis.2026.106050_b41","doi-asserted-by":"crossref","unstructured":"G.V. Horn, O.M. Aodha, Y. Song, et al., The inaturalist species classification and detection dataset, in: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2018, pp. 8769\u20138778.","DOI":"10.1109\/CVPR.2018.00914"},{"key":"10.1016\/j.imavis.2026.106050_b42","first-page":"1513","article-title":"Long-tailed classification by keeping the good and removing the bad momentum causal effect","author":"Tang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106050_b43","doi-asserted-by":"crossref","unstructured":"B. Zhou, Q. Cui, X.S. Wei, et al., Bbn: Bilateral-branch network with cumulative learning for long-tailed visual recognition, in: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 9716\u20139725.","DOI":"10.1109\/CVPR42600.2020.00974"},{"key":"10.1016\/j.imavis.2026.106050_b44","doi-asserted-by":"crossref","unstructured":"Y. Hong, S. Han, K. Choi, et al., Disentangling label distribution for long-tailed visual recognition, in: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 6622\u20136632.","DOI":"10.1109\/CVPR46437.2021.00656"},{"key":"10.1016\/j.imavis.2026.106050_b45","unstructured":"B.Y. Kang, S.N. Xie, M. Rohrbach, et al., Decoupling representation and classifier for long-tailed recognition, in: International Conference on Learning Representations, ICLR, 2019."},{"key":"10.1016\/j.imavis.2026.106050_b46","doi-asserted-by":"crossref","unstructured":"S. Park, J. Lim, Y. Jeon, et al., Influence-balanced loss for imbalanced visual classification, in: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 715\u2013724.","DOI":"10.1109\/ICCV48922.2021.00077"},{"key":"10.1016\/j.imavis.2026.106050_b47","unstructured":"M. Ren, W. Zeng, B. Yang, et al., Learning to reweight examples for robust deep learning, in: 2018 International Conference on Machine Learning, ICML, 2018, pp. 4334\u20134343."},{"key":"10.1016\/j.imavis.2026.106050_b48","doi-asserted-by":"crossref","unstructured":"Z.S. Zhong, J.Q. Cui, S. Liu, et al., Improving calibration for long-tailed recognition, in: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 16484\u201316493.","DOI":"10.1109\/CVPR46437.2021.01622"},{"key":"10.1016\/j.imavis.2026.106050_b49","doi-asserted-by":"crossref","unstructured":"M.K. Li, Y.M. Cheung, Y. Lu, Long-tailed visual recognition via gaussian clouded logit adjustment, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 6919\u20136928.","DOI":"10.1109\/CVPR52688.2022.00680"},{"key":"10.1016\/j.imavis.2026.106050_b50","series-title":"Exploring weight balancing on long-tailed recognition problem","author":"Hasegawa","year":"2023"},{"issue":"3","key":"10.1016\/j.imavis.2026.106050_b51","first-page":"3695","article-title":"Reslt: Residual learning for long-tailed recognition","volume":"45","author":"Cui","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.106050_b52","first-page":"7139","article-title":"Towards calibrated model for long-tailed visual recognition from prior perspective","author":"Xu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst. (NIPS)"},{"key":"10.1016\/j.imavis.2026.106050_b53","doi-asserted-by":"crossref","unstructured":"T.H. Li, P. Cao, Y. Yuan, et al., Targeted supervised contrastive learning for long-tailed recognition, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 6908\u20136918.","DOI":"10.1109\/CVPR52688.2022.00679"},{"key":"10.1016\/j.imavis.2026.106050_b54","unstructured":"B.Y. Kang, S.N. Xie, M. Rohrbach, Decoupling Representation and Classifier for Long-Tailed Recognition, in: International Conference on Learning Representations, ICLR, 2019."},{"key":"10.1016\/j.imavis.2026.106050_b55","doi-asserted-by":"crossref","unstructured":"J.L. Liu, W.H. Li, Y.F. Sun, Memory-based jitter: Improving visual recognition on long-tailed data with diversity in memory, in: Proceedings of the AAAI conference on artificial intelligence, AAAI, 2022, pp. 1720\u20131728.","DOI":"10.1609\/aaai.v36i2.20064"},{"key":"10.1016\/j.imavis.2026.106050_b56","first-page":"19290","article-title":"Rethinking the value of labels for improving class-imbalanced learning","author":"Yang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst. (NIPS)"},{"key":"10.1016\/j.imavis.2026.106050_b57","unstructured":"B.Y. Kang, Y. Li, S. Xie, et al., Exploring balanced feature spaces for representation learning, in: International Conference on Learning Representations, ICLR, 2020."},{"key":"10.1016\/j.imavis.2026.106050_b58","doi-asserted-by":"crossref","unstructured":"P. Wang, K. Han, X.S. Wei, Contrastive learning based hybrid networks for long-tailed image classification, in: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 943\u2013952.","DOI":"10.1109\/CVPR46437.2021.00100"},{"key":"10.1016\/j.imavis.2026.106050_b59","doi-asserted-by":"crossref","unstructured":"S.Y. Zhang, Z.M. Li, S.P. Yan, et al., Distribution alignment: A unified framework for long-tail visual recognition, in: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 2361\u20132370.","DOI":"10.1109\/CVPR46437.2021.00239"},{"key":"10.1016\/j.imavis.2026.106050_b60","doi-asserted-by":"crossref","unstructured":"X. Chen, Y. Zhou, D. Wu, et al., Area: adaptive reweighting via effective area for long-tailed classification, in: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 19220\u201319230.","DOI":"10.1109\/ICCV51070.2023.01766"},{"key":"10.1016\/j.imavis.2026.106050_b61","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.imavis.2026.106050_b62","doi-asserted-by":"crossref","unstructured":"M. Lou, Y.Z. Yu, Overlock: An overview-first-look-closely-next convnet with context-mixing dynamic kernels, in: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2025, pp. 128\u2013138.","DOI":"10.1109\/CVPR52734.2025.00021"},{"key":"10.1016\/j.imavis.2026.106050_b63","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110470","article-title":"ScopeViT: Scale-aware vision transformer","volume":"153","author":"Nie","year":"2024","journal-title":"Pattern Recognit."},{"issue":"5","key":"10.1016\/j.imavis.2026.106050_b64","doi-asserted-by":"crossref","first-page":"3123","DOI":"10.1109\/TPAMI.2023.3341806","article-title":"Crossformer++: A versatile vision transformer hinging on cross-scale attention","volume":"45","author":"Wang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001575?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001575?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T06:25:32Z","timestamp":1784528732000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885626001575"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":64,"alternative-id":["S0262885626001575"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106050","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Semantic-preserving augmentation with saliency-aware geometric fusion for long-tailed visual recognition","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106050","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"}],"article-number":"106050"}}