{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:03:02Z","timestamp":1780416182361,"version":"3.54.1"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach. Intell. Res."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s11633-025-1574-0","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T06:48:49Z","timestamp":1775544529000},"page":"711-725","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Bidirectional Hybrid Network for Food Image Recognition"],"prefix":"10.1007","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6098-1023","authenticated-orcid":false,"given":"Shuying","family":"Hong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0716-0918","authenticated-orcid":false,"given":"Donglin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0199-5001","authenticated-orcid":false,"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"issue":"8","key":"1574_CR1","doi-asserted-by":"publisher","first-page":"9932","DOI":"10.1109\/TPAMI.2023.3237871","volume":"45","author":"W Min","year":"2023","unstructured":"W. Min, Z. Wang, Y. Liu, M. Luo, L. Kang, X. Wei, X. Wei, S. Jiang. Large scale visual food recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 8, pp. 9932\u20139949, 2023. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2023.3237871.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"1574_CR2","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1109\/TAFE.2024.3392985","volume":"2","author":"V F Annese","year":"2024","unstructured":"V. F. Annese, V. Galli, G. Coco, M. Caironi. Organic nontoxic rechargeable batteries in food packaging: A feasibility study. IEEE Transactions on AgriFood Electronics, vol. 2, no. 2, pp. 252\u2013258, 2024. DOI: https:\/\/doi.org\/10.1109\/TAFE.2024.3392985.","journal-title":"IEEE Transactions on AgriFood Electronics"},{"issue":"2","key":"1574_CR3","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1109\/TAFE.2024.3415124","volume":"2","author":"B Alsaid","year":"2024","unstructured":"B. Alsaid, T. Saroufil, R. Berim, S. Majzoub, A. J. Hussain. Food physical contamination detection using ai-enhanced electrical impedance tomography. IEEE Transactions on AgriFood Electronics, vol. 2, no. 2, pp. 518\u2013526, 2024. DOI: https:\/\/doi.org\/10.1109\/TAFE.2024.3415124.","journal-title":"IEEE Transactions on AgriFood Electronics"},{"key":"1574_CR4","doi-asserted-by":"publisher","unstructured":"D. Zhang, B. Ma, X. J. Wu. Adaptive feature fusion and enhancement network for food nutrition estimation. IEEE Transactions on AgriFood Electronics, to be published. DOI: https:\/\/doi.org\/10.1109\/TAFE.2025.3555504.","DOI":"10.1109\/TAFE.2025.3555504"},{"issue":"4","key":"1574_CR5","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1007\/s11633-022-1358-8","volume":"20","author":"M Han","year":"2023","unstructured":"M. Han, Y. Zhan, B. Yu, Y. Luo, H. Hu, B. Du, Y. Wen, D. Tao. Region-adaptive concept aggregation for few-shot visual recognition. Machine Intelligence Research, vol. 20, no. 4, pp. 554\u2013568, 2023. DOI: https:\/\/doi.org\/10.1007\/s11633-022-1358-8.","journal-title":"Machine Intelligence Research"},{"issue":"5","key":"1574_CR6","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1007\/s11633-022-1340-5","volume":"19","author":"Y Wu","year":"2022","unstructured":"Y. Wu, D. H. Wang, X. T. Lu, F. Yang, M. Yao, W. S. Dong, J. B. Shi, G. Q. Li. Efficient visual recognition: A survey on recent advances and brain-inspired methodologies. Machine Intelligence Research, vol. 19, no. 5, pp. 366\u2013411, 2022. DOI: https:\/\/doi.org\/10.1007\/s11633-022-1340-5.","journal-title":"Machine Intelligence Research"},{"issue":"5","key":"1574_CR7","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1007\/s11633-022-1370-z","volume":"19","author":"X L Zou","year":"2022","unstructured":"X. L. Zou, T. J. Huang, S. Wu. Towards a new paradigm for brain-inspired computer vision. Machine Intelligence Research, vol. 19, no. 5, pp. 412\u2013424, 2022. DOI: https:\/\/doi.org\/10.1007\/s11633-022-1370-z.","journal-title":"Machine Intelligence Research"},{"key":"1574_CR8","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1007\/978-3-030-88007-1_43","volume-title":"Proceedings of the 4th Chinese Conference on Pattern Recognition and Computer Vision","author":"D Zhang","year":"2021","unstructured":"D. Zhang, X. J. Wu, J. Yu. Discrete bidirectional matrix factorization hashing for zero-shot cross-media retrieval. In Proceedings of the 4th Chinese Conference on Pattern Recognition and Computer Vision, Springer, Beijing, China, pp. 524\u2013536, 2021. DOI: https:\/\/doi.org\/10.1007\/978-3-030-88007-1_43."},{"key":"1574_CR9","doi-asserted-by":"publisher","unstructured":"M. Li, H. Wang, Z. Wan. Surface defect detection of steel strips based on improved YOLOv4. Computers and Electrical Engineering, vol. 102, Article number 108208, 2022. DOI: https:\/\/doi.org\/10.1016\/j.compeleceng.2022.108208.","DOI":"10.1016\/j.compeleceng.2022.108208"},{"key":"1574_CR10","doi-asserted-by":"publisher","unstructured":"J. Liu, X. Wang. Plant diseases and pests detection based on deep learning: A review. Plant Methods, vol. 17, no. 1, Article number 22, 2021. DOI: https:\/\/doi.org\/10.1186\/s13007-021-00722-9.","DOI":"10.1186\/s13007-021-00722-9"},{"issue":"3","key":"1574_CR11","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/s11390-016-1642-6","volume":"31","author":"X J Zhang","year":"2016","unstructured":"X. J. Zhang, Y. F. Lu, S. H. Zhang. Multi-task learning for food identification and analysis with deep convolutional neural networks. Journal of Computer Science and Technology, vol. 31, no. 3, pp. 489\u2013500, 2016. DOI: https:\/\/doi.org\/10.1007\/s11390-016-1642-6.","journal-title":"Journal of Computer Science and Technology"},{"issue":"2","key":"1574_CR12","doi-asserted-by":"publisher","first-page":"731","DOI":"10.32604\/cmc.2020.06508","volume":"62","author":"L Pan","year":"2020","unstructured":"L. Pan, C. Li, S. Pouyanfar, R. Chen, Y. Zhou. A novel combinational convolutional neural network for automatic food-ingredient classification. Computers, Materials & Continua, vol. 62, no. 2, pp. 731\u2013746, 2020. DOI: https:\/\/doi.org\/10.32604\/cmc.2020.06508.","journal-title":"Computers, Materials & Continua"},{"key":"1574_CR13","doi-asserted-by":"publisher","unstructured":"S. Jiang, W. Min, Y. Lyu, L. Liu. Few-shot food recognition via multi-view representation learning. ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 16, no. 3, Article number 87, 2020. DOI: https:\/\/doi.org\/10.1145\/3391624.","DOI":"10.1145\/3391624"},{"key":"1574_CR14","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/ICIIBMS.2018.8550005","volume-title":"Proceedings of International Conference on Intelligent Informatics and Biomedical Sciences","author":"M T Islam","year":"2018","unstructured":"M. T. Islam, B. M. N. K. Siddique, S. Rahman, T. Jabid. Food image classification with convolutional neural network. In Proceedings of International Conference on Intelligent Informatics and Biomedical Sciences, IEEE, Bangkok, Thailand, pp. 257\u2013262, 2018. DOI: https:\/\/doi.org\/10.1109\/ICIIBMS.2018.8550005."},{"issue":"4","key":"1574_CR15","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1109\/JSTSP.2020.2969328","volume":"14","author":"H Zhao","year":"2020","unstructured":"H. Zhao, K. H. Yap, A. C. Kot, L. Duan. JDNet: A joint-learning distilled network for mobile visual food recognition. IEEE Journal of Selected Topics in Signal Processing, vol. 14, no. 4, pp. 665\u2013675, 2020. DOI: https:\/\/doi.org\/10.1109\/JSTSP.2020.2969328.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"issue":"2","key":"1574_CR16","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1109\/TAFE.2024.3386713","volume":"2","author":"G Sheng","year":"2024","unstructured":"G. Sheng, W. Min, T. Yao, J. Song, Y. Yang, L. Wang, S. Jiang. Lightweight food image recognition with global shuffle convolution. IEEE Transactions on AgriFood Electronics, vol. 2, no. 2, pp. 392\u2013402, 2024. DOI: https:\/\/doi.org\/10.1109\/TAFE.2024.3386713.","journal-title":"IEEE Transactions on AgriFood Electronics"},{"key":"1574_CR17","doi-asserted-by":"publisher","first-page":"9992","DOI":"10.1109\/ICCV48922.2021.00986","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"Z Liu","year":"2021","unstructured":"Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Montreal, Canada, pp. 9992\u201310002, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986."},{"key":"1574_CR18","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1109\/ICCV48922.2021.00060","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"L Yuan","year":"2021","unstructured":"L. Yuan, Y. Chen, T. Wang, W. Yu, Y. Shi, Z. Jiang, F. E. H. Tay, J. Feng, S. Yan. Tokens-to-token ViT: Training vision transformers from scratch on ImageNet. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Montreal, Canada, pp. 538\u2013547, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.00060."},{"issue":"6","key":"1574_CR19","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"A. Krizhevsky, I. Sutskever, G. E. Hinton. ImageNet classification with deep convolutional neural networks. Communications of the ACM, vol. 60, no. 6, pp. 84\u201390, 2017. DOI: https:\/\/doi.org\/10.1145\/3065386.","journal-title":"Communications of the ACM"},{"key":"1574_CR20","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"K He","year":"2016","unstructured":"K. He, X. Zhang, S. Ren, J. Sun. Deep residual learning for image recognition. In Proceedings of Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, pp. 770\u2013778, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.90."},{"key":"1574_CR21","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1145\/3394171.3414031","volume-title":"Proceedings of the 28th ACM International Conference on Multimedia","author":"W Min","year":"2020","unstructured":"W. Min, L. Liu, Z. Wang, Z. Luo, X. Wei, X. Wei, S. Jiang. ISIA food-500: A dataset for large-scale food recognition via stacked global-local attention network. In Proceedings of the 28th ACM International Conference on Multimedia, ACM, Seattle, USA, pp. 393\u2013401, 2020. DOI: https:\/\/doi.org\/10.1145\/3394171.3414031."},{"key":"1574_CR22","doi-asserted-by":"publisher","unstructured":"B. Ma, D. Zhang, X. J. Wu. Food nutrition estimation with RGB-D fusion module and bidirectional feature pyramid network. Multimedia Systems, vol. 31, no. 2, Article number 140, 2025. DOI: https:\/\/doi.org\/10.1007\/s00530-025-01732-6.","DOI":"10.1007\/s00530-025-01732-6"},{"key":"1574_CR23","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2015.7169816","volume-title":"Proceedings of International Conference on Multimedia & Expo Workshops","author":"K Yanai","year":"2015","unstructured":"K. Yanai, Y. Kawano. Food image recognition using deep convolutional network with pre-training and fine-tuning. In Proceedings of International Conference on Multimedia & Expo Workshops, IEEE, Turin, Italy, 2015. DOI: https:\/\/doi.org\/10.1109\/ICMEW.2015.7169816."},{"key":"1574_CR24","doi-asserted-by":"publisher","unstructured":"D. Zhang, X. J. Wu. Robust and discrete matrix factorization hashing for cross-modal retrieval. Pattern Recognition, vol. 122, Article number 108343, 2022. DOI: https:\/\/doi.org\/10.1016\/j.patcog.2021.108343.","DOI":"10.1016\/j.patcog.2021.108343"},{"key":"1574_CR25","doi-asserted-by":"publisher","unstructured":"D. Zhang, X. J. Wu, J. Yu. Label consistent flexible matrix factorization hashing for efficient cross-modal retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 17, no. 3, Article number 90, 2021. DOI: https:\/\/doi.org\/10.1145\/3446774.","DOI":"10.1145\/3446774"},{"key":"1574_CR26","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, [Online], Available: https:\/\/arxiv.org\/abs\/1704.04861, 2017."},{"key":"1574_CR27","doi-asserted-by":"publisher","first-page":"6848","DOI":"10.1109\/CVPR.2018.00716","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"X Zhang","year":"2018","unstructured":"X. Zhang, X. Zhou, M. Lin, J. Sun. ShuffleNet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, pp. 6848\u20136856, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00716."},{"key":"1574_CR28","doi-asserted-by":"publisher","first-page":"5987","DOI":"10.1109\/CVPR.2017.634","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"S Xie","year":"2017","unstructured":"S. Xie, R. Girshick, P. Doll\u00e1r, Z. Tu, K. He. Aggregated residual transformations for deep neural networks. In Proceedings of Conference on Computer Vision and Pattern Recognition, IEEE, Honolulu, USA, pp. 5987\u20135995, 2017. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.634."},{"key":"1574_CR29","doi-asserted-by":"publisher","first-page":"2261","DOI":"10.1109\/CVPR.2017.243","volume-title":"Proceedings of Conference on Computer Vision and Pattern Recognition","author":"G Huang","year":"2017","unstructured":"G. Huang, Z. Liu, L. Van Der Maaten, K. Q. Weinberger. Densely connected convolutional networks. In Proceedings of Conference on Computer Vision and Pattern Recognition, IEEE, Honolulu, USA, pp. 2261\u20132269, 2017. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.243."},{"key":"1574_CR30","doi-asserted-by":"publisher","first-page":"7132","DOI":"10.1109\/CVPR.2018.00745","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Hu","year":"2018","unstructured":"J. Hu, L. Shen, G. Sun. Squeeze-and-excitation networks. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, pp. 7132\u20137141, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00745."},{"key":"1574_CR31","first-page":"6105","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"M Tan","year":"2019","unstructured":"M. Tan, Q. Le. EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning, Long Beach, USA, pp. 6105\u20136114, 2019."},{"key":"1574_CR32","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1109\/ICCV48922.2021.00061","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"W Wang","year":"2021","unstructured":"W. Wang, E. Xie, X. Li, D. P. Fan, K. Song, D. Liang, T. Lu, P. Luo, L. Shao. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Montreal, Canada, pp. 548\u2013558, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.00061."},{"key":"1574_CR33","doi-asserted-by":"publisher","first-page":"3687","DOI":"10.1109\/CVPR52729.2023.00359","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S Ren","year":"2023","unstructured":"S. Ren, F. Wei, Z. Zhang, H. Hu. TinyMIM: An empirical study of distilling MIM pre-trained models. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Vancouver, Canada, pp. 3687\u20133697, 2023. DOI: https:\/\/doi.org\/10.1109\/CVPR52729.2023.00359."},{"key":"1574_CR34","doi-asserted-by":"publisher","first-page":"12239","DOI":"10.1109\/ICCV48922.2021.01204","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"B Graham","year":"2021","unstructured":"B. Graham, A. El-Nouby, H. Touvron, P. Stock, A. Joulin, H. J\u00e9gou, M. Douze. LeViT: A vision transformer in ConvNet\u2019s clothing for faster inference. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Montreal, Canada, pp. 12239\u201312249, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.01204."},{"key":"1574_CR35","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1109\/ICCV48922.2021.00041","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"C F R Chen","year":"2021","unstructured":"C. F. R. Chen, Q. Fan, R. Panda. CrossViT: Cross-attention multi-scale vision transformer for image classification. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Montreal, Canada, pp. 347\u2013356, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.00041."},{"key":"1574_CR36","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/ICCV48922.2021.00009","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"H Wu","year":"2021","unstructured":"H. Wu, B. Xiao, N. Codella, M. Liu, X. Dai, L. Yuan, L. Zhang. CvT: Introducing convolutions to vision transformers. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Montreal, Canada, pp. 22\u201331, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.00009."},{"issue":"6","key":"1574_CR37","doi-asserted-by":"publisher","first-page":"11534","DOI":"10.1109\/TNNLS.2025.3550979","volume":"36","author":"M Lou","year":"2025","unstructured":"M. Lou, S. Zhang, H. Y. Zhou, S. Yang, C. Wu, Y. Yu. TransXNet: Learning both global and local dynamics with a dual dynamic token mixer for visual recognition. IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 6, pp. 11534\u201311547, 2025. DOI: https:\/\/doi.org\/10.1109\/TNNLS.2025.3550979.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"2","key":"1574_CR38","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TPAMI.2022.3164083","volume":"45","author":"Y Li","year":"2023","unstructured":"Y. Li, T. Yao, Y. Pan, T. Mei. Contextual transformer networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 2, pp. 1489\u20131500, 2023. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2022.3164083.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1574_CR39","volume-title":"Proceedings of the 10th International Conference on Learning Representations","author":"S Mehta","year":"2022","unstructured":"S. Mehta, M. Rastegari. MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer. In Proceedings of the 10th International Conference on Learning Representations, 2022."},{"key":"1574_CR40","doi-asserted-by":"publisher","first-page":"15909","DOI":"10.1109\/CVPR52733.2024.01506","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"A Wang","year":"2024","unstructured":"A. Wang, H. Chen, Z. Lin, J. Han, G. Ding. Rep ViT: Revisiting mobile CNN from ViT perspective. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 15909\u201315920, 2024. DOI: https:\/\/doi.org\/10.1109\/CVPR52733.2024.01506."},{"key":"1574_CR41","doi-asserted-by":"publisher","unstructured":"B. Chen, M. Wei, J. Liu, H. Li, C. Dai, J. Liu, Z. Ji. EFS-YOLO: A lightweight network based on steel strip surface defect detection. Measurement Science and Technology, vol. 35, no. 11, Article number 116003, 2024. DOI: https:\/\/doi.org\/10.1088\/1361-6501\/ad66fe.","DOI":"10.1088\/1361-6501\/ad66fe"},{"key":"1574_CR42","doi-asserted-by":"publisher","unstructured":"G. Sheng, W. Min, X. Zhu, L. Xu, Q. Sun, Y. Yang, L. Wang, S. Jiang. A lightweight hybrid model with location-preserving ViT for efficient food recognition. Nutrients, vol. 16, no. 2, Article number 200, 2024. DOI: https:\/\/doi.org\/10.3390\/nu16020200.","DOI":"10.3390\/nu16020200"},{"key":"1574_CR43","doi-asserted-by":"publisher","unstructured":"Y. Yang, W. Min, J. Song, G. Sheng, L. Wang, S. Jiang. Lightweight food recognition via aggregation block and feature encoding. ACM Transactions on Multimedia Computing, Communications and Applications, vol. 20, no. 10, Article number 327, 2024. DOI: https:\/\/doi.org\/10.1145\/3680285.","DOI":"10.1145\/3680285"},{"issue":"7","key":"1574_CR44","doi-asserted-by":"publisher","first-page":"1926","DOI":"10.1109\/JBHI.2020.2987943","volume":"24","author":"F P W Lo","year":"2020","unstructured":"F. P. W. Lo, Y. Sun, J. Qiu, B. Lo. Image-based food classification and volume estimation for dietary assessment: A review. IEEE Journal of Biomedical and Health Informatics, vol. 24, no. 7, pp. 1926\u20131939, 2020. DOI: https:\/\/doi.org\/10.1109\/JBHI.2020.2987943.","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"1574_CR45","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1109\/MIPR.2019.00056","volume-title":"Proceedings of Conference on Multimedia Information Processing and Retrieval","author":"T Ege","year":"2019","unstructured":"T. Ege, Y. Ando, R. Tanno, W. Shimoda, K. Yanai. Image-based estimation of real food size for accurate food calorie estimation. In Proceedings of Conference on Multimedia Information Processing and Retrieval, IEEE, San Jose, USA, pp. 274\u2013279, 2019. DOI: https:\/\/doi.org\/10.1109\/MIPR.2019.00056."},{"key":"1574_CR46","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1109\/ICME.2009.5202718","volume-title":"Proceedings of International Conference on Multimedia and Expo","author":"W Wu","year":"2009","unstructured":"W. Wu, J. Yang. Fast food recognition from videos of eating for calorie estimation. In Proceedings of International Conference on Multimedia and Expo, IEEE, New York, USA, pp. 1210\u20131213, 2009. DOI: https:\/\/doi.org\/10.1109\/ICME.2009.5202718."},{"key":"1574_CR47","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1109\/ACPR.2017.145","volume-title":"Proceedings of the 4th IAPR Asian Conference on Pattern Recognition","author":"T Ege","year":"2017","unstructured":"T. Ege, K. Yanai. Estimating food calories for multiple-dish food photos. In Proceedings of the 4th IAPR Asian Conference on Pattern Recognition, IEEE, Nanjing, China, pp. 646\u2013651, 2017. DOI: https:\/\/doi.org\/10.1109\/ACPR.2017.145."},{"key":"1574_CR48","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1109\/ICSCC59169.2023.10335053","volume-title":"Proceedings of the 9th International Conference on Smart Computing and Communications","author":"E D Cherpanath","year":"2023","unstructured":"E. D. Cherpanath, P. R. F. Nasreen, K. Pradeep, M. Menon, V. S. Jayanthi. Food image recognition and calorie prediction using faster R-CNN and mask R-CNN. In Proceedings of the 9th International Conference on Smart Computing and Communications, IEEE, Kochi, India, pp. 83\u201389, 2023. DOI: https:\/\/doi.org\/10.1109\/ICSCC59169.2023.10335053."},{"key":"1574_CR49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSAAI59313.2023.10452481","volume-title":"Proceedings of International Conference on Data Science, Agents & Artificial Intelligence","author":"R P Guru","year":"2023","unstructured":"R. P. Guru, M. Ayyadurai, T. Amirthalakshmi, R. Neelaven, K. Sujatha. Calorie recognition from food images using CNN for nutritional analysis. In Proceedings of International Conference on Data Science, Agents & Artificial Intelligence, IEEE, Chennai, India, 2023. DOI: https:\/\/doi.org\/10.1109\/ICDSAAI59313.2023.10452481."},{"key":"1574_CR50","doi-asserted-by":"publisher","DOI":"10.1109\/ECTI-CON58255.2023.10153183","volume-title":"Proceedings of the 20th International Conference on Electrical Engineering\/Electronics, Computer, Telecommunications and Information Technology","author":"R Sombutkaew","year":"2023","unstructured":"R. Sombutkaew, O. Chitsobhuk. Image-based Thai food recognition and calorie estimation using machine learning techniques. In Proceedings of the 20th International Conference on Electrical Engineering\/Electronics, Computer, Telecommunications and Information Technology, IEEE, Nakhon Phanom, Thailand, 2023. DOI: https:\/\/doi.org\/10.1109\/ECTI-CON58255.2023.10153183."},{"key":"1574_CR51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT61001.2024.10725324","volume-title":"Proceedings of the 15th International Conference on Computing Communication and Networking Technologies","author":"M Suneela","year":"2024","unstructured":"M. Suneela, M. Sahithi, N. Vamsi, N. B. Naik, N. S. Chowdary. Enhancing dietary monitoring using deep learning: Food recognition and calorie estimation. In Proceedings of the 15th International Conference on Computing Communication and Networking Technologies, IEEE, Kamand, India, 2024. DOI: https:\/\/doi.org\/10.1109\/ICCCNT61001.2024.10725324."},{"key":"1574_CR52","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCECE60827.2024.10548096","volume-title":"Proceedings of the 3rd International Conference on Distributed Computing and Electrical Circuits and Electronics","author":"Q Sun","year":"2024","unstructured":"Q. Sun. Food image classification and food safety detection based on pretrained convolutional neural network. In Proceedings of the 3rd International Conference on Distributed Computing and Electrical Circuits and Electronics, IEEE, Ballari, India, 2024. DOI: https:\/\/doi.org\/10.1109\/ICDCECE60827.2024.10548096."},{"key":"1574_CR53","doi-asserted-by":"publisher","first-page":"6869","DOI":"10.1109\/IEMBS.2009.5333123","volume-title":"Proceedings of 2009 Annual International Conference of the Engineering in Medicine and Biology Society","author":"C K Martin","year":"2009","unstructured":"C. K. Martin, S. Kaya, B. K. Gunturk. Quantification of food intake using food image analysis. In Proceedings of 2009 Annual International Conference of the Engineering in Medicine and Biology Society, IEEE, Minneapolis, USA, pp. 6869\u20136872, 2009. DOI: https:\/\/doi.org\/10.1109\/IEMBS.2009.5333123."},{"key":"1574_CR54","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Proceedings of the 13th European Conference on Computer Vision","author":"L Bossard","year":"2014","unstructured":"L. Bossard, M. Guillaumin, L. Van Gool. Food-101-mining discriminative components with random forests. In Proceedings of the 13th European Conference on Computer Vision, Springer, Zurich, Switzerland, pp. 446\u2013461, 2014. DOI: https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29."},{"key":"1574_CR55","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1145\/2964284.2964315","volume-title":"Proceedings of the 24th International Conference on Multimedia","author":"J Chen","year":"2016","unstructured":"J. Chen, C. W. Ngo. Deep-based ingredient recognition for cooking recipe retrieval. In Proceedings of the 24th International Conference on Multimedia, ACM, Amsterdam, The Netherlands, pp. 32\u201341, 2016. DOI: https:\/\/doi.org\/10.1145\/2964284.2964315."},{"key":"1574_CR56","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1145\/2638728.2641339","volume-title":"Proceedings of the International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication","author":"Y Kawano","year":"2014","unstructured":"Y. Kawano, K. Yanai. Food image recognition with deep convolutional features. In Proceedings of the International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication, ACM, Seattle, USA, pp. 589\u2013593, 2014. DOI: https:\/\/doi.org\/10.1145\/2638728.2641339."},{"key":"1574_CR57","doi-asserted-by":"publisher","unstructured":"W. Min, Z. Wang, J. Yang, C. Liu, S. Jiang. Vision-based fruit recognition via multi-scale attention CNN. Computers and Electronics in Agriculture, vol. 210, Article number 107911, 2023. DOI: https:\/\/doi.org\/10.1016\/j.compag.2023.107911.","DOI":"10.1016\/j.compag.2023.107911"},{"key":"1574_CR58","doi-asserted-by":"publisher","first-page":"11966","DOI":"10.1109\/CVPR52688.2022.01167","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Liu","year":"2022","unstructured":"Z. Liu, H. Mao, C. Y. Wu, C. Feichtenhofer, T. Darrell, S. Xie. A ConvNet for the 2020s. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, New Orleans, USA, pp. 11966\u201311976, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.01167."},{"key":"1574_CR59","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/j.neucom.2016.11.100","volume":"277","author":"A Jalalvand","year":"2018","unstructured":"A. Jalalvand, K. Demuynck, W. De Neve, J. P. Martens. On the application of reservoir computing networks for noisy image recognition. Neurocomputing, vol. 277, pp. 237\u2013248, 2018. DOI: https:\/\/doi.org\/10.1016\/j.neucom.2016.11.100.","journal-title":"Neurocomputing"},{"key":"1574_CR60","doi-asserted-by":"publisher","unstructured":"N. K. Kalantari, T. C. Wang, R. Ramamoorthi. Learning-based view synthesis for light field cameras. ACM Transactions on Graphics, vol. 35, no. 6, Article number 193, 2016. DOI: https:\/\/doi.org\/10.1145\/2980179.2980251.","DOI":"10.1145\/2980179.2980251"},{"key":"1574_CR61","first-page":"3","volume-title":"Proceedings of European Conference on Computer Vision","author":"Y Kawano","year":"2014","unstructured":"Y. Kawano, K. Yanai. Automatic expansion of a food image dataset leveraging existing categories with domain adaptation. In Proceedings of European Conference on Computer Vision, Zurich, Switzerland, pp. 3\u201317, 2014."}],"container-title":["Machine Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-025-1574-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11633-025-1574-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-025-1574-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T15:03:16Z","timestamp":1780412596000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11633-025-1574-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,7]]},"references-count":61,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["1574"],"URL":"https:\/\/doi.org\/10.1007\/s11633-025-1574-0","relation":{},"ISSN":["2731-538X","2731-5398"],"issn-type":[{"value":"2731-538X","type":"print"},{"value":"2731-5398","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,7]]},"assertion":[{"value":"27 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no conflicts of interest related to this work.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations of conflict of interest"}}]}}