{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T17:21:53Z","timestamp":1770830513427,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2017YFF0108800"],"award-info":[{"award-number":["2017YFF0108800"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["N2005032"],"award-info":[{"award-number":["N2005032"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Foundation of military logistics science and technology of China","award":["CLB8C050"],"award-info":[{"award-number":["CLB8C050"]}]},{"name":"Key projects of Natural Science Foundation of Liaoning Province","award":["2017012074-301"],"award-info":[{"award-number":["2017012074-301"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1007\/s00521-020-05312-9","type":"journal-article","created":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T18:45:46Z","timestamp":1598985946000},"page":"5151-5166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Two-branch encoding and iterative attention decoding network for semantic segmentation"],"prefix":"10.1007","volume":"33","author":[{"given":"Hegui","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4378-5381","authenticated-orcid":false,"given":"Xiangde","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,1]]},"reference":[{"issue":"4","key":"5312_CR1","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"A Karpathy","year":"2015","unstructured":"Karpathy A, Li FF (2015) Deep visual-semantic alignments for generating image descriptions. IEEE Trans Pattern Anal Mach Intell 39(4):664\u2013676","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5312_CR2","unstructured":"Xu K, Ba J, Kiros R et al (2015) Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of the advances in international conference on machine learning, pp 2048\u20132057"},{"key":"5312_CR3","doi-asserted-by":"crossref","unstructured":"Aneja J, Deshpande A, Schwing AG (2018) Convolutional image captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5561\u20135570","DOI":"10.1109\/CVPR.2018.00583"},{"key":"5312_CR4","doi-asserted-by":"crossref","unstructured":"Papandreou G, Kokkinos I, Savalle PA (2015) Modeling local and global deformations in deep learning: epitomic convolution, multiple instance learning, and sliding window detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 390\u2013399","DOI":"10.1109\/CVPR.2015.7298636"},{"key":"5312_CR5","unstructured":"Dai J, Li Y, He K et al (2016) R\u2013FCN: object detection via region-based fully convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 379\u2013387"},{"issue":"2","key":"5312_CR6","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1109\/LGRS.2018.2872355","volume":"16","author":"C Wang","year":"2019","unstructured":"Wang C, Bai X, Wang S et al (2019) Multiscale visual attention networks for object detection in VHR remote sensing images. IEEE Geosci Remote Sens Lett 16(2):310\u2013314","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"5312_CR7","doi-asserted-by":"crossref","unstructured":"Kaneko AM, Yamamoto K (2016) Landmark recognition based on image characterization by segmentation points for autonomous driving. In: IEEE sice international symposium on control systems (ISCS), pp 1\u20138","DOI":"10.1109\/SICEISCS.2016.7470160"},{"key":"5312_CR8","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"5312_CR9","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556"},{"key":"5312_CR10","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"5312_CR11","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"5312_CR12","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"12","key":"5312_CR13","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\u2013decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5312_CR14","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"11","key":"5312_CR15","doi-asserted-by":"publisher","first-page":"3954","DOI":"10.1109\/JSTARS.2018.2833382","volume":"11","author":"R Li","year":"2018","unstructured":"Li R, Liu W, Yang L et al (2018) DeepUNet: a deep fully convolutional network for pixel-level sea-land segmentation. IEEE J Sel Top Appl Earth Observ Remote Sens 11(11):3954\u20133962","journal-title":"IEEE J Sel Top Appl Earth Observ Remote Sens"},{"key":"5312_CR16","unstructured":"Chen LC, Papandreou G, Kokkinos I et al (2014) Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv preprint arXiv:14127062"},{"key":"5312_CR17","doi-asserted-by":"crossref","unstructured":"Lin G, Milan A, Shen C et al (2017) Refinenet: Multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1925\u20131934","DOI":"10.1109\/CVPR.2017.549"},{"key":"5312_CR18","doi-asserted-by":"crossref","unstructured":"Yu C, Wang J, Peng C et al (2018) Learning a discriminative feature network for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1857\u20131866","DOI":"10.1109\/CVPR.2018.00199"},{"key":"5312_CR19","unstructured":"Chen LC, Papandreou G, Schroff F et al (2017) Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:170605587"},{"key":"5312_CR20","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X et al (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"issue":"4","key":"5312_CR21","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen LC, Papandreou G, Kokkinos I et al (2017) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5312_CR22","doi-asserted-by":"crossref","unstructured":"Chen LC, Zhu Y, Papandreou G et al (2018) Encoder\u2013decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision (ECCV), pp 801\u2013818","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"5312_CR23","unstructured":"Wu H, Zhang J, Huang K et al (2019) FastFCN: rethinking dilated convolution in the backbone for semantic segmentation. arXiv preprint arXiv:190311816"},{"key":"5312_CR24","doi-asserted-by":"crossref","unstructured":"Yu C, Wang J, Peng C et al (2018) Bisenet: bilateral segmentation network for real-time semantic segmentation. In: Proceedings of the European conference on computer vision (ECCV), pp 325\u2013341","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"5312_CR25","doi-asserted-by":"crossref","unstructured":"Zheng S, Jayasumana S, Romeraparedes B et al (2015) Conditional random feilds as recurrent nerual networks. In: International conference on computer vision, pp 1529\u20131537","DOI":"10.1109\/ICCV.2015.179"},{"key":"5312_CR26","doi-asserted-by":"crossref","unstructured":"Peng C, Zhang X, Yu G et al (2017) Large kernel matters\u2013improve semantic segmentation by global convolutional network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4353\u20134361","DOI":"10.1109\/CVPR.2017.189"},{"key":"5312_CR27","doi-asserted-by":"crossref","unstructured":"Chen LC, Yang Y, Wang J et al (2016) Attention to scale: scale-aware semantic image segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3640\u20133649","DOI":"10.1109\/CVPR.2016.396"},{"key":"5312_CR28","doi-asserted-by":"crossref","unstructured":"Chen L, Zhang H, Xiao J et al (2017) SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5659\u20135667","DOI":"10.1109\/CVPR.2017.667"},{"key":"5312_CR29","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, pp 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"},{"key":"5312_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-020-10240-9","author":"H Zhu","year":"2020","unstructured":"Zhu H, Miao Y, Zhang X (2020) Semantic image segmentation with improved position attention and feature fusion. Neural Proces Lett. https:\/\/doi.org\/10.1007\/s11063-020-10240-9","journal-title":"Neural Proces Lett"},{"key":"5312_CR31","unstructured":"Howard AG, Zhu M, Chen B et al (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:170404861"},{"key":"5312_CR32","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M et al (2018) Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6848\u20136856","DOI":"10.1109\/CVPR.2018.00716"},{"key":"5312_CR33","doi-asserted-by":"crossref","unstructured":"Li H, Xiong P, Fan H et al (2019) DFAnet: deep feature aggregation for real-time semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9522\u20139531","DOI":"10.1109\/CVPR.2019.00975"},{"key":"5312_CR34","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01671-x","author":"HG Zhu","year":"2020","unstructured":"Zhu HG, Wang BY, Zhang XD et al (2020) Semantic image segmentation with shared decomposition convolution and boundary reinforcement structure. Appl Intell. https:\/\/doi.org\/10.1007\/s10489-020-01671-x","journal-title":"Appl Intell"},{"key":"5312_CR35","unstructured":"Wang RJ, Li X, Ling CX (2018) Pelee: a real-time object detection system on mobile devices. In: Advances in neural information processing systems, pp 1963\u20131972"},{"key":"5312_CR36","doi-asserted-by":"crossref","unstructured":"Noh H, Hong S, Han B (2015) Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 1520\u20131528","DOI":"10.1109\/ICCV.2015.178"},{"key":"5312_CR37","doi-asserted-by":"crossref","unstructured":"Visin F, Ciccone M, Romero A et al (2016) Reseg: a recurrent neural network-based model for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 41\u201348","DOI":"10.1109\/CVPRW.2016.60"},{"key":"5312_CR38","doi-asserted-by":"crossref","unstructured":"J\u00e9gou S, Drozdzal M, Vazquez D et al (2017) The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 11\u201319","DOI":"10.1109\/CVPRW.2017.156"},{"key":"5312_CR39","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122"},{"key":"5312_CR40","doi-asserted-by":"crossref","unstructured":"Kundu A, Vineet V, Koltun V (2016) Feature space optimization for semantic video segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1925\u20131934","DOI":"10.1109\/CVPR.2016.345"},{"key":"5312_CR41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2895460","author":"J Liu","year":"2017","unstructured":"Liu J, Wang Y et al (2017) Stacked deconvolutional network for semantic segmentation. IEEE Trans Image Process. https:\/\/doi.org\/10.1109\/TIP.2019.2895460","journal-title":"IEEE Trans Image Process"},{"key":"5312_CR42","unstructured":"Molchanov P, Tyree S, Karras T et al (2016) Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440"},{"key":"5312_CR43","doi-asserted-by":"crossref","unstructured":"Zhao H, Qi X, Shen X et al (2018) Icnet for real-time semantic segmentation on high-resolution images. In: Proceedings of the European conference on computer vision (ECCV), pp 405\u2013420","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"5312_CR44","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Fowlkes C (2016) Laplacian pyramid reconstruction and refinement for semantic segmentation. In: European conference on computer vision, pp 519\u2013534","DOI":"10.1007\/978-3-319-46487-9_32"},{"issue":"11","key":"5312_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TMM.2019.2957953","volume":"21","author":"T Zhang","year":"2019","unstructured":"Zhang T, Lin G, Cai J et al (2019) Decoupled spatial neural attention for weakly supervised semantic segmentation. IEEE Trans Multimed 21(11):1\u201311","journal-title":"IEEE Trans Multimed"},{"issue":"7","key":"5312_CR46","doi-asserted-by":"publisher","first-page":"1476","DOI":"10.1109\/TPAMI.2016.2601099","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren S, He K, Girshick R et al (2016) Object detection networks on convolutional feature maps. IEEE Trans Pattern Anal Mach Intell 39(7):1476\u20131481","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5312_CR47","doi-asserted-by":"crossref","unstructured":"Mostajabi M, Yadollahpour P, Shakhnarovich G (2015) Feedforward semantic segmentation with zoom-out features. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3376\u20133385","DOI":"10.1109\/CVPR.2015.7298959"},{"issue":"17","key":"5312_CR48","doi-asserted-by":"publisher","first-page":"22159","DOI":"10.1007\/s11042-018-5704-3","volume":"77","author":"Y Liu","year":"2018","unstructured":"Liu Y, Yu J, Han Y (2018) Understanding the effective receptive field in semantic image segmentation. Multimed Tools Appl 77(17):22159\u201322171","journal-title":"Multimed Tools Appl"},{"key":"5312_CR49","doi-asserted-by":"crossref","unstructured":"Vemulapalli R, Tuzel O, Liu MY et al (2016) Gaussian conditional random field network for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3224\u20133233","DOI":"10.1109\/CVPR.2016.351"},{"key":"5312_CR50","doi-asserted-by":"crossref","unstructured":"Liu Z, Li X, Luo P et al (2015) Semantic image segmentation via deep parsing network. In: International conference on computer vision, pp 1377\u20131385","DOI":"10.1109\/ICCV.2015.162"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05312-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-020-05312-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05312-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T02:18:40Z","timestamp":1630462720000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-020-05312-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,1]]},"references-count":50,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["5312"],"URL":"https:\/\/doi.org\/10.1007\/s00521-020-05312-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,1]]},"assertion":[{"value":"9 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 September 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}