{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:04:46Z","timestamp":1783699486308,"version":"3.55.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"The Natural Science Foundation of Shandong Province, China","award":["ZR2020QC174"],"award-info":[{"award-number":["ZR2020QC174"]}]},{"name":"College Students' Innovative Entrepreneurial Training Plan Program","award":["S202210430062"],"award-info":[{"award-number":["S202210430062"]}]},{"name":"The Taishan Scholar Advantage Characteristic Discipline Talent Team Project of Shandong Province of China","award":["2015162"],"award-info":[{"award-number":["2015162"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11554-024-01521-w","type":"journal-article","created":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T20:17:42Z","timestamp":1722889062000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["WoodGLNet: a multi-scale network integrating global and local information for real-time classification of wood images"],"prefix":"10.1007","volume":"21","author":[{"given":"Zhishuai","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhedong","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhikang","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxia","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yucheng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,5]]},"reference":[{"issue":"11","key":"1521_CR1","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"2016","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (2016)","journal-title":"Proc. IEEE"},{"key":"1521_CR2","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Sun, S., et al. Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1521_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.imavis.2024.104987","volume":"145","author":"K Atrey","year":"2024","unstructured":"Atrey, K., Singh, B.K., Bodhey, N.K.: Integration of ultrasound and mammogram for multimodal classification of breast cancer using hybrid residual neural network and machine learning. Image Vis. Comput. 145, 1\u20139 (2024)","journal-title":"Image Vis. Comput."},{"key":"1521_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.imavis.2024.104945","volume":"143","author":"X Han","year":"2024","unstructured":"Han, X., Li, T., Bai, C., et al.: Integrating prior knowledge into a bibranch pyramid network for medical image segmentation. Image Vis. Comput. 143, 1\u201315 (2024)","journal-title":"Image Vis. Comput."},{"key":"1521_CR5","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: CVPR, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1521_CR6","first-page":"234","volume":"9351","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Thomas, B.: U-Net: convolutional networks for biomedical image segmentation. MICCAI 9351, 234\u2013241 (2015)","journal-title":"MICCAI"},{"key":"1521_CR7","doi-asserted-by":"crossref","unstructured":"Sun, K, Xiao, B., Liu, D., et al.: Deep high-resolution representation learning for human pose estimation. In: CVPR, pp. 5686\u20135696 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"issue":"8","key":"1521_CR8","first-page":"2011","volume":"42","author":"H Jie","year":"2020","unstructured":"Jie, H., Li, S., Albanie, S., et al.: Squeeze-and-excitation networks. CVPR 42(8), 2011\u20132023 (2020)","journal-title":"CVPR"},{"key":"1521_CR9","unstructured":"Yue, C., Jiaru, X., Lin, S., et al.: GCNet: non-local networks meet squeeze-excitation networks and beyond. In: ICCV, pp. 1971\u20131980 (2019)"},{"key":"1521_CR10","first-page":"3","volume":"11211","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., et al.: CBAM: convolutional block attention module. ECCV 11211, 3\u201319 (2018)","journal-title":"ECCV"},{"key":"1521_CR11","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jia, J., Koltun, V.: Exploring self-attention for image recognition. In: CVPR, pp. 10076\u201310085 (2020)","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"1521_CR12","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., et al.: Relation networks for object detection. In: CVPR, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"1521_CR13","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A. et al.: Non-local neural networks. In: CVPR, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1521_CR14","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. NIPS 30, 5998\u20136008 (2017)","journal-title":"NIPS"},{"key":"1521_CR15","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR, pp. 1\u201322 (2021)"},{"key":"1521_CR16","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et al.: End-to-end object detection with transformer. In: ECCV, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1521_CR17","unstructured":"Zhu, X.,Su, W., Lu, L., et al.: Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR, pp. 1\u201312 (2021)"},{"key":"1521_CR18","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., et al.: Segmenter: transformer for semantic segmentation. In: ICCV, pp. 7262\u20137272 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"1521_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.imavis.2023.104872","volume":"141","author":"N Shahadat","year":"2024","unstructured":"Shahadat, N., Maida, A.S.: Cross channel weight sharing for image classification. Image Vis. Comput. 141, 1\u201315 (2024)","journal-title":"Image Vis. Comput."},{"key":"1521_CR20","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: ICCV, pp. 548\u2013558 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"1521_CR21","doi-asserted-by":"crossref","unstructured":"Yuan, K. Guo, S., Liu, Z., et al.: Incorporating convolution designs into visual transformers. In: ICCV, pp. 559\u2013568 (2021)","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"1521_CR22","first-page":"7358","volume":"139","author":"H Touvron","year":"2021","unstructured":"Touvron, H., Cord, M., Douze, M., et al.: Training data-efficient image transformers & distillation through attention. PMLR 139, 7358\u20137367 (2021)","journal-title":"PMLR"},{"key":"1521_CR23","first-page":"3965","volume":"34","author":"Z Dai","year":"2021","unstructured":"Dai, Z., Liu, H., Le, Q.V., et al.: CoAtNet: marrying convolution and attention for all data sizes. NeurIPS 34, 3965\u20133977 (2021)","journal-title":"NeurIPS"},{"key":"1521_CR24","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wu, Q., Wang, J., et al.: Mixformer: mixing features across windows and dimensions. In: CVPR, pp. 5239\u20135249 (2022)","DOI":"10.1109\/CVPR52688.2022.00518"},{"key":"1521_CR25","doi-asserted-by":"crossref","unstructured":"Guo, J., Han, K., Wu, H., et al.: CMT: convolutional neural networks meet vision transformers. In: CVPR, pp. 12175\u201312185 (2022)","DOI":"10.1109\/CVPR52688.2022.01186"},{"issue":"8","key":"1521_CR26","doi-asserted-by":"publisher","first-page":"9454","DOI":"10.1109\/TPAMI.2023.3243048","volume":"45","author":"Z Peng","year":"2023","unstructured":"Peng, Z., Huang, W., Shanzhi, G., et al.: Conformer: local features coupling global representations for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 9454\u20139468 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1521_CR27","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Chen, D., et al.: Mobileformer: bridging mobilenet and transformer. In: CVPR, pp. 5260\u20135269 (2022)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"1521_CR28","unstructured":"Lou, M., Zhou, H.-Y., Yang, S., et al.: TransXNet: learning both global and local dynamics with a dual dynamic token mixer for visual recognition. In: CVPR, pp. 1\u201312 (2023)"},{"key":"1521_CR29","unstructured":"Han, K., Xiao, A., Wu, E., et al.: Transformer in transformer. In: NeurIPS, pp. 1\u201314 (2021)"},{"key":"1521_CR30","doi-asserted-by":"crossref","unstructured":"Yuan, L., Chen, Y., Wang, T., et al.: Tokens-to token vit: training vision transformers from scratch on imagenet. In: ICCV, pp. 538\u2013547 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"1521_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR, pp. 1\u201314 (2015)"},{"key":"1521_CR32","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: CVPR, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1521_CR33","first-page":"7358","volume":"139","author":"H Touvron","year":"2021","unstructured":"Touvron, H., Cord, M., Douze, M., et al.: Training data-efficient image transformers & distillation through attention. ICML. 139, 7358\u20137367 (2021)","journal-title":"ICML."},{"key":"1521_CR34","doi-asserted-by":"crossref","unstructured":"Lee, Y., Kim, J., Willette, J., et al.: MPViT: multi-path vision transformer for dense prediction. In: CVPR, pp. 7277\u20137286 (2022)","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"1521_CR35","unstructured":"Chu, X., Tian, Z., Wang, Y., et al.: Twins: revisiting the design of spatial attention in vision transformers. In: NeurIPS, pp. 1\u201312 (2021)"},{"key":"1521_CR36","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., et al.: CvT: introducing convolutions to vision transformers. In: ICCV, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"1521_CR37","doi-asserted-by":"crossref","unstructured":"Liu, X., Peng, H., Zheng, N., et al.: EfficientViT: memory efficient vision transformer with cascaded group attention. In: CVPR, pp. 14420\u201314430 (2023)","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"1521_CR38","unstructured":"Jiang, Z., Hou, Q., Yuan, L., et al.: All tokens matter: token labeling for training better vision transformers. In: NeurIPS, pp. 1\u201316 (2021)"},{"issue":"8","key":"1521_CR39","first-page":"1","volume":"14","author":"Q Feng","year":"2022","unstructured":"Feng, Q., Li, P., Zhixun, L., et al.: EViT: privacy-preserving image retrieval via encrypted vision transformer in cloud computing. IEEE Trans. Circuits Syst. Video Technol. 14(8), 1\u201320 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1521_CR40","unstructured":"Ge, C., Ding, X., Tong, Z., et al.: Advancing vision transformers with group-mix attention. In: CVPR, pp. 1\u201314 (2023)"},{"key":"1521_CR41","unstructured":"Chen, Z., Zhang, Y., Gu, J., et al.: Recursive generalization transformer for image super-resolution. In: ICLR, pp. 1\u201312 (2024)"},{"key":"1521_CR42","unstructured":"Li, C., Zhou, A., Yao, A.: Omni-dimensional dynamic convolution. In: ICLR, pp. 1\u201320 (2022)"},{"key":"1521_CR43","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Liu, M., et al.: Dynamic convolution: attention over convolution kernels. In: CVPR, pp. 11027\u201311036 (2020)","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"1521_CR44","unstructured":"Zhang, X., Song, Y., Song, T., et al.: AKConv: convolutional kernel with arbitrary sampled shapes and arbitrary number of parameters. In: CVPR, pp. 1\u201310 (2023)"},{"issue":"3","key":"1521_CR45","first-page":"415","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., Xie, E., Li, X., et al.: PVT v2: improved baselines with pyramid vision transformer. CVMJ 8(3), 415\u2013424 (2022)","journal-title":"CVMJ"},{"key":"1521_CR46","first-page":"6105","volume":"97","author":"M Tan","year":"2019","unstructured":"Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. ICML 97, 6105\u20136114 (2019)","journal-title":"ICML"},{"key":"1521_CR47","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y. Cao, Y., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1521_CR48","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T., Parmar, N., et al.: Bottleneck transformers for visual recognition. In: CVPR, pp. 16514\u201316524 (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"1521_CR49","first-page":"9335","volume":"34","author":"X Chu","year":"2021","unstructured":"Chu, X., Tian, Z., Wang, Y., et al.: Twins: revisiting the design of spatial attention in vision transformers. NeurIPS 34, 9335\u20139366 (2021)","journal-title":"NeurIPS"},{"key":"1521_CR50","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning Multiple Layers of Features from Tiny Images, pp. 1\u201360 (2009)"},{"key":"1521_CR51","first-page":"4905","volume":"29","author":"W Luo","year":"2016","unstructured":"Luo, W., Li, Y., Urtasun, R., et al.: Understanding the effective receptive field in deep convolutional neural networks. NIPS 29, 4905\u20134913 (2016)","journal-title":"NIPS"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01521-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-024-01521-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01521-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T16:03:52Z","timestamp":1724774632000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-024-01521-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["1521"],"URL":"https:\/\/doi.org\/10.1007\/s11554-024-01521-w","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]},"assertion":[{"value":"23 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2024","order":3,"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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"147"}}