{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T10:36:58Z","timestamp":1760524618472,"version":"3.37.3"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"8-9","license":[{"start":{"date-parts":[[2024,5,18]],"date-time":"2024-05-18T00:00:00Z","timestamp":1715990400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,18]],"date-time":"2024-05-18T00:00:00Z","timestamp":1715990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Central Government Guided Local Funds for Science and Technology Development","award":["216Z0301G"],"award-info":[{"award-number":["216Z0301G"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61379065"],"award-info":[{"award-number":["61379065"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Hebei Natural Science Foundation","doi-asserted-by":"crossref","award":["F2023203012"],"award-info":[{"award-number":["F2023203012"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Science Research Project of Hebei Education Department","award":["QN2024010"],"award-info":[{"award-number":["QN2024010"]}]},{"name":"Innovation Capability Improvement Plan Project of Hebei Province","award":["22567626H"],"award-info":[{"award-number":["22567626H"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s11760-024-03255-5","type":"journal-article","created":{"date-parts":[[2024,5,18]],"date-time":"2024-05-18T11:01:50Z","timestamp":1716030110000},"page":"5579-5588","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Harmonizing local and global features: enhanced hand gesture segmentation using synergistic fusion of CNN and transformer networks"],"prefix":"10.1007","volume":"18","author":[{"given":"Shi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maohua","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shihui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,18]]},"reference":[{"issue":"8","key":"3255_CR1","doi-asserted-by":"publisher","first-page":"3963","DOI":"10.1007\/s11760-023-02626-8","volume":"17","author":"A Aggarwal","year":"2023","unstructured":"Aggarwal, A., Bhutani, N., Kapur, R., Dhand, G., Sheoran, K.: Real-time hand gesture recognition using multiple deep learning architectures. Signal Image Video Process. 17(8), 3963\u20133971 (2023)","journal-title":"Signal Image Video Process."},{"issue":"8","key":"3255_CR2","doi-asserted-by":"publisher","first-page":"2019","DOI":"10.1007\/s11760-022-02163-w","volume":"16","author":"JP Sahoo","year":"2022","unstructured":"Sahoo, J.P., Sahoo, S.P., Ari, S., Patra, S.K.: Rbi-2rcnn: residual block intensity feature using a two-stage residual convolutional neural network for static hand gesture recognition. Signal Image Video Process. 16(8), 2019\u20132027 (2022)","journal-title":"Signal Image Video Process."},{"issue":"8","key":"3255_CR3","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1007\/s11760-021-01930-5","volume":"15","author":"Y Jiang","year":"2021","unstructured":"Jiang, Y., Zhao, M., Wang, C., Wei, F., Wang, K., Qi, H.: Diver\u2019s hand gesture recognition and segmentation for human-robot interaction on AUV. Signal Image Video Process. 15(8), 1899\u20131906 (2021)","journal-title":"Signal Image Video Process."},{"key":"3255_CR4","doi-asserted-by":"crossref","unstructured":"Urooj, A., Borji, A.: Analysis of hand segmentation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4710\u20134719 (2018)","DOI":"10.1109\/CVPR.2018.00495"},{"issue":"1","key":"3255_CR5","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.32604\/iasc.2023.032832","volume":"36","author":"S Gnanapriya","year":"2023","unstructured":"Gnanapriya, S., Rahimunnisa, K.: A hybrid deep learning model for real time hand gestures recognition. Intell. Autom. Soft Comput. 36(1), 1105\u20131119 (2023). https:\/\/doi.org\/10.32604\/iasc.2023.032832","journal-title":"Intell. Autom. Soft Comput."},{"key":"3255_CR6","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/s10055-016-0301-0","volume":"21","author":"KM Sagayam","year":"2017","unstructured":"Sagayam, K.M., Hemanth, D.J.: Hand posture and gesture recognition techniques for virtual reality applications: a survey. Virtual Real. 21, 91\u2013107 (2017)","journal-title":"Virtual Real."},{"key":"3255_CR7","unstructured":"Kayalibay, B., Jensen, G., Smagt, P.: Cnn-based segmentation of medical imaging data (2017). arXiv preprint arXiv:1701.03056"},{"key":"3255_CR8","first-page":"1","volume":"60","author":"C Peng","year":"2021","unstructured":"Peng, C., Zhang, K., Ma, Y., Ma, J.: Cross fusion net: a fast semantic segmentation network for small-scale semantic information capturing in aerial scenes. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"3255_CR9","volume":"16","author":"M Liu","year":"2024","unstructured":"Liu, M., Shi, W., Zhao, L., Beyette, F.R., Jr.: Best performance with fewest resources: unveiling the most resource-efficient convolutional neural network for P300 detection with the aid of Explainable AI. Mach. Learn. Appl. 16, 100542 (2024)","journal-title":"Mach. Learn. Appl."},{"key":"3255_CR10","first-page":"12116","volume":"34","author":"M Raghu","year":"2021","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? Adv. Neural Inf. Process. Syst. 34, 12116\u201312128 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3255_CR11","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L.: CVT: introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"3255_CR12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3302024","author":"Y Liu","year":"2023","unstructured":"Liu, Y., Zhang, Y., Wang, Y., Mei, S.: Rethinking transformers for semantic segmentation of remote sensing images. IEEE Trans. Geosci. Remote Sens. (2023). https:\/\/doi.org\/10.1109\/TGRS.2023.3302024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"8","key":"3255_CR13","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1049\/iet-cvi.2018.5796","volume":"13","author":"A Dadashzadeh","year":"2019","unstructured":"Dadashzadeh, A., Targhi, A.T., Tahmasbi, M., Mirmehdi, M.: Hgr-net: a fusion network for hand gesture segmentation and recognition. IET Comput. Vis. 13(8), 700\u2013707 (2019)","journal-title":"IET Comput. Vis."},{"issue":"2","key":"3255_CR14","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1080\/09540091.2019.1670621","volume":"32","author":"Z Xu","year":"2020","unstructured":"Xu, Z., Zhang, W.: Hand segmentation pipeline from depth map: an integrated approach of histogram threshold selection and shallow cnn classification. Connect. Sci. 32(2), 162\u2013173 (2020)","journal-title":"Connect. Sci."},{"key":"3255_CR15","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention-MICCAI, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3255_CR16","doi-asserted-by":"crossref","unstructured":"Wang, W., Yu, K., Hugonot, J., Fua, P., Salzmann, M.: Recurrent u-net for resource-constrained segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2142\u20132151 (2019)","DOI":"10.1109\/ICCV.2019.00223"},{"issue":"1","key":"3255_CR17","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1007\/s00138-022-01360-4","volume":"34","author":"Z Yang","year":"2023","unstructured":"Yang, Z., Wang, Q., Zeng, J., Qin, P., Chai, R., Sun, D.: Rau-net: U-net network based on residual multi-scale fusion and attention skip layer for overall spine segmentation. Mach. Vis. Appl. 34(1), 10 (2023)","journal-title":"Mach. Vis. Appl."},{"key":"3255_CR18","doi-asserted-by":"publisher","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with Atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) COMPUTER VISION\u2013ECCV 2018, pp. 833\u2013851 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49","DOI":"10.1007\/978-3-030-01234-2_49"},{"issue":"10","key":"3255_CR19","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Xiao, B.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349\u20133364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3255_CR20","unstructured":"Hong, Y., Pan, H., Sun, W., Jia, Y.: Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes (2021). arXiv preprint arXiv:2101.06085"},{"key":"3255_CR21","doi-asserted-by":"crossref","unstructured":"Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., Wang, M.: Swin- unet: Unet-like pure transformer for medical image segmentation. In: European Conference on Computer Vision, pp. 205\u2013218 (2022)","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"3255_CR22","doi-asserted-by":"crossref","unstructured":"Wang H., Cao P., Liu X., Yang J., Zaiane O.: Narrowing the semantic gaps in U-Net with learnable skip connections: the case of medical image segmentation (2023). arXiv preprint arXiv:2312.15182","DOI":"10.1016\/j.neunet.2024.106546"},{"key":"3255_CR23","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., Zhou, Y.: Transunet: transformers make strong encoders for medical image segmentation (2021). arXiv preprint arXiv:2102.04306"},{"key":"3255_CR24","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, D., Xu, C., Wang, W., Hong, Q., Li, Q., Tian, J.: TFCNs: a CNN-transformer hybrid network for medical image segmentation. In: International Conference on Artificial Neural Networks, pp. 781\u2013792 (2022)","DOI":"10.1007\/978-3-031-15937-4_65"},{"key":"3255_CR25","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 418\u2013434 (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"3255_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3255_CR27","doi-asserted-by":"publisher","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803. IEEE, Salt Lake City, UT, USA (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00813","DOI":"10.1109\/CVPR.2018.00813"},{"key":"3255_CR28","doi-asserted-by":"publisher","unstructured":"Matilainen, M., Sangi, P., Holappa, J., Silven, O.: OUHANDS database for hand detection and pose recognition. In: 2016 6th International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 1\u20135. IEEE, Oulu, Finland (2016). https:\/\/doi.org\/10.1109\/IPTA.2016.7821025","DOI":"10.1109\/IPTA.2016.7821025"},{"key":"3255_CR29","unstructured":"HGR1. http:\/\/sun.aei.polsl.pl\/mkawulok\/gestures\/"},{"key":"3255_CR30","doi-asserted-by":"crossref","unstructured":"Bambach, S., Lee, S., Crandall, D.J., Yu, C.: Lending a hand: detecting hands and recognizing activities in complex egocentric interactions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1949\u20131957 (2015)","DOI":"10.1109\/ICCV.2015.226"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03255-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03255-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03255-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T10:00:33Z","timestamp":1732010433000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03255-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,18]]},"references-count":30,"journal-issue":{"issue":"8-9","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["3255"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03255-5","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2024,5,18]]},"assertion":[{"value":"28 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2024","order":4,"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":"Competing interests"}}]}}