{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:22:07Z","timestamp":1772119327798,"version":"3.50.1"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:00:00Z","timestamp":1742601600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:00:00Z","timestamp":1742601600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Research on Key Technologies for Collecting and Accurately Evaluating Lycium barbarum Germplasm Resources","award":["2024BBF02011"],"award-info":[{"award-number":["2024BBF02011"]}]},{"name":"Research on Key Technologies for Collecting and Accurately Evaluating Lycium barbarum Germplasm Resources","award":["2024BBF02011"],"award-info":[{"award-number":["2024BBF02011"]}]},{"name":"Research on Key Technologies for Collecting and Accurately Evaluating Lycium barbarum Germplasm Resources","award":["2024BBF02011"],"award-info":[{"award-number":["2024BBF02011"]}]},{"name":"Research on Key Technologies for Collecting and Accurately Evaluating Lycium barbarum Germplasm Resources","award":["2024BBF02011"],"award-info":[{"award-number":["2024BBF02011"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s00371-025-03862-4","type":"journal-article","created":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T01:32:16Z","timestamp":1742693536000},"page":"8169-8179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CAS-FGvit: an efficient convolutional additive mixer for fine-grained classification"],"prefix":"10.1007","volume":"41","author":[{"given":"Fangyan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengju","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunsheng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojie","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,22]]},"reference":[{"key":"3862_CR1","unstructured":"Wah C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical Report CNS-TR-2011-001, California Institute of Technology, 2011"},{"key":"3862_CR2","doi-asserted-by":"crossref","unstructured":"Van Horn, G., Branson, S., Farrell, R., Haber, S., Barry, J., Ipeirotis, P., Perona, P., Belongie, S.: Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, 595\u2013604.","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"3862_CR3","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inform. Process. Syst. 25, 1097\u20131105 (2012)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"3862_CR4","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. 3rd International conference on learning representations (ICLR 2015), 2015, 1\u201314."},{"key":"3862_CR5","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Rabinovich, A.: Going deeper with convolutions. In Proceedings of the IEEE Conference on computer vision and pattern recognition, 2015, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"3862_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"3862_CR7","doi-asserted-by":"crossref","unstructured":"Ge, W., Lin, X., Yu, Y.: Weakly supervised complementary parts models for fine-grained image classification from the bottom up. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2019a, 3034\u20133043","DOI":"10.1109\/CVPR.2019.00315"},{"key":"3862_CR8","doi-asserted-by":"crossref","unstructured":"Liu, C., Xie, H., Zha, Z.-J., Ma, L., Yu, L., Zhang, Y.: Filtration and distillation: Enhancing region attention for fine-grained visual categorization. In Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34:11555\u201311562","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"3862_CR9","doi-asserted-by":"crossref","unstructured":"Ding, Y., Zhou, Y., Zhu, Y., Ye, Q., Jiao, J.: Selective sparse sampling for fine-grained image recognition. In Proceedings of the IEEE\/CVF international conference on computer vision, 2019, 6599\u20136608.","DOI":"10.1109\/ICCV.2019.00670"},{"key":"3862_CR10","first-page":"315","volume":"22","author":"W Chen","year":"2009","unstructured":"Chen, W., Liu, T.-Y., Lan, Y., Ma, Z.-M., Li, H.: Ranking measures and loss functions in learning to rank. Adv. Neural. Inf. Process. Syst. 22, 315\u2013323 (2009)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3862_CR11","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words:Transformers for image recognition at scale, 2020. arXiv preprintarXiv:2010.11929"},{"key":"3862_CR12","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In European conference on computer vision, 2020, 213\u2013229. Springer","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3862_CR13","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y.,Feng, J., Xiang, T., Torr, P. H., et al.: Rethinking semanticsegmentation from a sequence-to-sequence perspective with transformers. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2021, 6881\u20136890.","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"3862_CR14","doi-asserted-by":"crossref","unstructured":"Xie, E., Wang, W., Wang, W., Sun, P., Xu, H., Liang, D., and Luo, P.: Trans2Seg: transparent object segmentation with transformer, 2021","DOI":"10.24963\/ijcai.2021\/165"},{"key":"3862_CR15","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L.,Yuille, A. L., and Zhou, Y.: Transunet: Transformers make strong encoders for medical image segmentation, 2021. arXiv preprint arXiv:2102.04306"},{"key":"3862_CR16","unstructured":"Chowdhury, A., Paul, D., Mai, Z., Gu, J. et al.: Prompt-CAM: a simpler interpretable transformer for fine-grained analysis. 2025.https:\/\/arxiv.org\/abs\/2501.09333"},{"key":"3862_CR17","first-page":"0031","volume":"146","author":"Xu Yang","year":"2024","unstructured":"Yang, Xu., Shanshan, Wu., Wang, B., Yang, M., Zebin, Wu., Yao, Y., Wei, Z.: Two-stage fine-grained image classification model based on multi-granularity feature fusion. Pattern Recogn. 146, 0031\u20133203 (2024)","journal-title":"Pattern Recogn."},{"key":"3862_CR18","unstructured":"Zhang, T., Li, L., Zhou, Y., Liu, W., Qian, C., Ji, X.: CAS-ViT: Convolutional additive self-attention vision transformers for efficient mobile applications, 2024. arXiv:2408.03703. https:\/\/arxiv.org\/abs\/2408.03703"},{"key":"3862_CR19","doi-asserted-by":"crossref","unstructured":"Ding, M., Xiao, B., Codella, N., Luo, P., Wang, J., and Yuan, L.: Davit: Dual attention vision transformers. In European conference on computer vision, 2022, 74\u201392. Springer","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"3862_CR20","doi-asserted-by":"crossref","unstructured":"Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., Yuan, Y.: EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2023, 14420\u201314430","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"3862_CR21","doi-asserted-by":"crossref","unstructured":"Pan, J., Bulat, A., Tan, F., Zhu, X., Dudziak, L., Li, H., Tzimiropoulos, G., and Martinez, B. Edgevits: Competing light-weight cnns on mobile devices with vision transformers. In European conference on computer vision, 2022, 294\u2013311. Springer","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"3862_CR22","doi-asserted-by":"crossref","unstructured":"Shaker, A., Maaz, M., Rasheed, H., Khan, S., Yang, M.-H., Khan, F. S.: SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications, 2023. arXiv preprint arXiv:2303.15446","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"3862_CR23","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics, 315\u2013323. JMLR workshop and conference proceedings, 2011"},{"key":"3862_CR24","doi-asserted-by":"crossref","unstructured":"He, J., Chen, J.-N., Liu, S., Kortylewski, A., Yang, C., Bai, Y., Wang, C.: TransFG: a transformer architecture for fine-grained, 2021, arXiv:2103.07976.","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"3862_CR25","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D Object Representations for Fine-Grained Categorization. In 4th international IEEE workshop on 3D representation and recognition (3dRR-13). Sydney, Australia, 2013","DOI":"10.1109\/ICCVW.2013.77"},{"key":"3862_CR26","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., and Fei-Fei, L.: Novel dataset for fine-grained image categorization. In First workshop on fine-grained visual categorization, IEEE conference on computer vision and pattern recognition. Colorado Springs, CO, 2011"},{"key":"3862_CR27","unstructured":"Hu, T., Xu, J., Huang, C., Qi, H., Huang, Q., Lu, Y.: Weakly supervised bilinear attention network for fine-grained visual classification, 2019, arXiv:1808.02152"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03862-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03862-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03862-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T13:18:23Z","timestamp":1754659103000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03862-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,22]]},"references-count":27,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["3862"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03862-4","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5818524\/v1","asserted-by":"object"}]},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,22]]},"assertion":[{"value":"24 February 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human or animal subjects performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and animal rights"}},{"value":"Informed consent was not required because no human or animals were involved.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}