{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:58:23Z","timestamp":1767142703784,"version":"build-2238731810"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T00:00:00Z","timestamp":1647302400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T00:00:00Z","timestamp":1647302400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s11042-022-12519-6","type":"journal-article","created":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T09:12:51Z","timestamp":1647335571000},"page":"21547-21562","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Fast semantic segmentation network with attention gate and multi-layer fusion"],"prefix":"10.1007","volume":"81","author":[{"given":"Yanping","family":"Tang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4375-1405","authenticated-orcid":false,"given":"Canlong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Qinghe","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Luyang","family":"Qian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,15]]},"reference":[{"issue":"12","key":"12519_CR1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"12519_CR2","doi-asserted-by":"crossref","unstructured":"Baek JY, Chelu IV, Iordache L et al (2018) Scene understanding networks for autonomous driving based on around view monitoring system[C]. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops. IEEE Computer Society Press, Los Alamitos, pp 961\u2013968","DOI":"10.1109\/CVPRW.2018.00142"},{"key":"12519_CR3","unstructured":"Brostow GJ, Shotton J, Fauqueur J (2008)"},{"issue":"4","key":"12519_CR4","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen LC, Papandreou G, Kokkinos I et al (2018) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[j]. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"12519_CR5","unstructured":"Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. In: The IEEE conference on computer vision and pattern recognition (CVPR)"},{"key":"12519_CR6","doi-asserted-by":"crossref","unstructured":"Chollet F (2017) Xception: deep learning with depthwise separable convolutions[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE Computer Society Press, Los Alamitos, pp 1800\u20131807","DOI":"10.1109\/CVPR.2017.195"},{"key":"12519_CR7","doi-asserted-by":"crossref","unstructured":"Cordts M et al, Omran M, ramos S (2016) The cityscapes dataset for semantic urban scene understanding[C]. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). IEEE","DOI":"10.1109\/CVPR.2016.350"},{"key":"12519_CR8","doi-asserted-by":"crossref","unstructured":"Ding H, Jiang X, Shuai B, Qun Liu A, Wang G (2018) Context contrasted feature and gated multi-scale aggregation for scene segmentation. In: The IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00254"},{"key":"12519_CR9","doi-asserted-by":"publisher","unstructured":"Everingham M, Eslami SMA, Van Gool L et al (2015) The pascal visual object classes challenge: a retrospective. Int Journal of Comput Vis 111(1):98\u2013136. https:\/\/doi.org\/10.1007\/s11263-014-0733-5","DOI":"10.1007\/s11263-014-0733-5"},{"key":"12519_CR10","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H et al (2019) Dual attention network for scene segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"12519_CR11","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of Comput. Vis. Pattern Recognit, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"12519_CR12","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"12519_CR13","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.neucom.2019.02.003","volume":"338","author":"F Lateef","year":"2019","unstructured":"Lateef F, Ruichek Y (2019) Survey on semantic segmentation using deep learning techniques. Neurocomputing 338:321\u2013348","journal-title":"Neurocomputing"},{"key":"12519_CR14","doi-asserted-by":"crossref","unstructured":"Lin G, Milan A, Shen C, Reid I (2017) Refinenet: Multi-path refinement networks for high-resolution semantic segmentation. In: The IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2017.549"},{"key":"12519_CR15","unstructured":"Liu P, Fels S, West N et al Human computer interaction design for mobile devices based on a smart healthcare architecture. arXiv:https:\/\/arxiv.org\/abs\/1902.03541?context=cs.HC"},{"key":"12519_CR16","doi-asserted-by":"crossref","unstructured":"Liu ZW, Li XX, Luo P et al (2015) Semantic image segmentation via deep parsing network[C]. In: Proceedings of the IEEE International conference on computer vision. IEEE Computer Society Press, Los Alamitos, pp 1377\u20131385","DOI":"10.1109\/ICCV.2015.162"},{"key":"12519_CR17","doi-asserted-by":"crossref","unstructured":"Liu S et al, Wang S, Liu X (2020) Fuzzy Detection aided real-time and robust visual tracking under complex environments[J]. IEEE Trans Fuzzy Syst PP(99):1\u20131","DOI":"10.1109\/TFUZZ.2020.3006520"},{"key":"12519_CR18","doi-asserted-by":"crossref","unstructured":"Liu S et al, Wang S, Liu X (2021) Human memory update strategy: a multi-layer template update mechanism for remote visual Monitoring[J]. IEEE Trans Multimed PP(99):1\u20131","DOI":"10.1109\/TMM.2021.3065580"},{"key":"12519_CR19","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE Computer Society Press, Los Alamitos, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"12519_CR20","doi-asserted-by":"crossref","unstructured":"Mehta S, Rastegari M, Caspi A et al (2018) ESPNEt: efficient spatial pyramid of dilated convolutions for semantic segmentation[C]. In: Proceedings of the European conference on computer vision. Springer, Heidelberg, pp 561\u2013580","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"12519_CR21","doi-asserted-by":"crossref","unstructured":"Min W, Song W, Yadong W (2019) Research on visual optimization method of medical image visualization[J]. J Comput-Aided Des Comput Graph 31(4):659\u2013667. (in Chinese)","DOI":"10.3724\/SP.J.1089.2019.17402"},{"key":"12519_CR22","unstructured":"Mnih V, Heess N, Graves A et al (2014) Recurrent models of visual attention[C]. In: Advances in neural information processing systems, pp 2204\u20132212"},{"key":"12519_CR23","unstructured":"Paszke A, Chaurasia A, Kim S et al (2019) ENet: a deep neural network architecture for real-time semantic segmentation. arXiv:https:\/\/arxiv.org\/abs\/1606.02147"},{"key":"12519_CR24","doi-asserted-by":"crossref","unstructured":"Peng C, Zhang X, Yu G et al (2017) Large kernel matters-improve semantic segmentation by global convolutional network[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE Computer Society Press, Los Alamitos, pp 1743\u20131751","DOI":"10.1109\/CVPR.2017.189"},{"issue":"1","key":"12519_CR25","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1109\/TITS.2017.2750080","volume":"19","author":"E Romera","year":"2018","unstructured":"Romera E, \u00e1lvarez JM, Bergasa LM et al (2018) ERFNEt: efficient residual factorized ConvNet for real-time semantic segmentation[J]. IEEE Trans Intell Transp Syst 19(1):263\u2013272","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"12519_CR26","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation[C]. In: Proceedings of the international conference on medical image computing and computer-assisted intervention, vol 9351. Springer, Heidelberg, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"12519_CR27","unstructured":"Tao S, Tianyi Z, Guodong L, et al. (2017) DiSAN: Directional Self-Attention Network for RNN\/CNN-free Language Understanding, arXiv:1709.04696"},{"key":"12519_CR28","doi-asserted-by":"crossref","unstructured":"Tsutsui S, Kerola T, Saito S et al (2018) Minimizing supervision for free-space segmentation[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops. IEEE Computer Society Press, Los Alamitos, pp 988\u2013997","DOI":"10.1109\/CVPRW.2018.00145"},{"key":"12519_CR29","doi-asserted-by":"crossref","unstructured":"Wang PQ, Chen PF, Yuan Y et al (2018) Understanding convolution for semantic segmentation[C]. In: Proceedings of the IEEE winter conference on applications of computer vision. IEEE Computer Society Press, Los Alamitos, pp 1451\u20131460","DOI":"10.1109\/WACV.2018.00163"},{"key":"12519_CR30","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"12519_CR31","doi-asserted-by":"publisher","unstructured":"Wang S, Liu X, Liu S et al (2021) Human short-long term cognitive memory mechanism for visual monitoring in IoT-assisted smart cities[J]. IEEE Internet of Things Journal, online first. https:\/\/doi.org\/10.1109\/JIOT.2021.3077600","DOI":"10.1109\/JIOT.2021.3077600"},{"key":"12519_CR32","unstructured":"Wenchao L, Yanfeng L, Yahui P et al (2019) Multimodal registration of chest MRI images based on structure compensation[J]. J Comput-Aided Des Comput Graph 31(3):447\u2013454 (in Chinese)"},{"key":"12519_CR33","unstructured":"Wu Z, Shen C, Hengel Avd (2017) Real-time semantic image segmentation via spatial sparsity. arXiv:https:\/\/arxiv.org\/abs\/1712.00213v1"},{"key":"12519_CR34","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv:https:\/\/arxiv.org\/abs\/1511.07122v3"},{"key":"12519_CR35","doi-asserted-by":"crossref","unstructured":"Yu CQ, Wang J, Peng C (2018) BiSeNet: bilateral segmentation network for real-time semantic segmentation[C]. In: Proceedings of the European conference on computer vision, pp 334\u2013349","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"12519_CR36","doi-asserted-by":"crossref","unstructured":"Yu CQ, Wang J, Peng C et al (2018) Learning a discriminative feature network for semantic segmentation[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1857\u20131866","DOI":"10.1109\/CVPR.2018.00199"},{"key":"12519_CR37","unstructured":"Yuan Y, Wang J (2018) Ocnet: Object context network for scene parsing. In: arXiv:1809.00916"},{"key":"12519_CR38","doi-asserted-by":"crossref","unstructured":"Zhang H, Dana K, Shi J et al (2018) Context encoding for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"12519_CR39","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou XY, Lin MX et al (2018) Shufflenet: an extremely efficient convolutional neural network for mobile devices[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE Computer Society Press, Los Alamitos, pp 6848\u20136856","DOI":"10.1109\/CVPR.2018.00716"},{"key":"12519_CR40","doi-asserted-by":"crossref","unstructured":"Zhao H, Qi X, Shen XY et al (2018) ICNEt for real-time semantic segmentation on high-resolution images[C] In: Proceedings of the European conference on computer vision. Springer, Heidelberg, pp 418\u2013434","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"12519_CR41","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. IEEE Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2017.660"},{"key":"12519_CR42","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X et al (2017) Pyramid scene parsing network[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE Computer Society Press, Los Alamitos, pp 6230\u20136239","DOI":"10.1109\/CVPR.2017.660"},{"key":"12519_CR43","doi-asserted-by":"crossref","unstructured":"Zhao H, Zhang Y, Liu S et al (2018) Psanet: Point-wise spatial attention network for scene parsing. In: Proceedings of the European conference on computer vision (ECCV), pp 270\u2013286","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"12519_CR44","doi-asserted-by":"crossref","unstructured":"Zheng SA, Jayasumana S, Romera-Paredes B et al (2015) Conditional random fields as recurrent neural networks[C]. In: Proceedings of the IEEE international conference on computer vision. IEEE Computer Society Press, Los Alamitos, pp 1529\u20131537","DOI":"10.1109\/ICCV.2015.179"}],"updated-by":[{"DOI":"10.1007\/s11042-022-13037-1","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T00:00:00Z","timestamp":1651190400000}}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12519-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-12519-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12519-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T02:26:50Z","timestamp":1653532010000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-12519-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,15]]},"references-count":44,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["12519"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-12519-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,15]]},"assertion":[{"value":"19 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 March 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2022","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s11042-022-13037-1","URL":"https:\/\/doi.org\/10.1007\/s11042-022-13037-1","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}