{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T18:24:16Z","timestamp":1743013456925,"version":"3.37.3"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T00:00:00Z","timestamp":1693612800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T00:00:00Z","timestamp":1693612800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16230-y","type":"journal-article","created":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T06:02:04Z","timestamp":1693634524000},"page":"37007-37023","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["PPNet : pooling position attention network for semantic segmentation"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8587-7044","authenticated-orcid":false,"given":"Haixia","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuailong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,2]]},"reference":[{"key":"16230_CR1","doi-asserted-by":"crossref","unstructured":"Otsu NA (1979) Threshold selection method from gray-level histograms. In: IEEE Trans Syst Man Cybern 9(1):62\u201366","DOI":"10.1109\/TSMC.1979.4310076"},{"key":"16230_CR2","doi-asserted-by":"crossref","unstructured":"Bezdek JC, Ehrlich R, Full W (1984) FCM: The fuzzy c-means clustering algorithm. Comput Geosci 10(2\u20133):191\u2013203","DOI":"10.1016\/0098-3004(84)90020-7"},{"key":"16230_CR3","unstructured":"Ng HP, Ong SH, Foong KWC et al (2006) Medical image segmentation using k-means clustering and improved watershed algorithm. In: 2006 IEEE southwest symposium on image analysis and interpretation. IEEE 2006: 61\u201365"},{"key":"16230_CR4","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. pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"16230_CR5","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"16230_CR6","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"},{"key":"16230_CR7","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\/CVF Conference on Computer Vision and Pattern Recognition. 2019: 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"},{"key":"16230_CR8","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A et al (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"16230_CR9","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang X, Huang L, et al (2019) Ccnet: Criss-cross attention for semantic segmentation.In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019: 603\u2013612","DOI":"10.1109\/ICCV.2019.00069"},{"key":"16230_CR10","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"},{"key":"16230_CR11","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Fowlkes CC (2016) Laplacian pyramid reconstruction and refinement for semantic segmentation. In: European conference on computer vision. Springer, Cham, pp 519\u2013534","DOI":"10.1007\/978-3-319-46487-9_32"},{"key":"16230_CR12","doi-asserted-by":"crossref","unstructured":"Kreso I, Causevic D, Krapac J et al (2016) Convolutional scale invariance for semantic segmentation. In: German Conference on Pattern Recognition. Springer, Cham, pp 64\u201375","DOI":"10.1007\/978-3-319-45886-1_6"},{"key":"16230_CR13","doi-asserted-by":"crossref","unstructured":"Liu Z, Li X, Luo P, et al (2015) Semantic image segmentation via deep parsing network. In: Proceedings of the IEEE international conference on computer vision. 2015: 1377\u20131385","DOI":"10.1109\/ICCV.2015.162"},{"key":"16230_CR14","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122"},{"key":"16230_CR15","doi-asserted-by":"crossref","unstructured":"Lin G, Shen C, Van Den Hengel A et al (2016) Efficient piecewise training of deep structured models for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 3194\u20133203","DOI":"10.1109\/CVPR.2016.348"},{"key":"16230_CR16","doi-asserted-by":"crossref","unstructured":"Yuan Y, Chen X, Wang J (2020) Object-contextual representations for semantic segmentation. In: European conference on computer vision. Springer, Cham, pp 173\u2013190","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"16230_CR17","doi-asserted-by":"crossref","unstructured":"Zheng S, Jayasumana S, Romera-Paredes B et al (2015) Conditional random fields as recurrent neural networks. In: Proceedings of the IEEE international conference on computer vision. 2015: 1529\u20131537","DOI":"10.1109\/ICCV.2015.179"},{"key":"16230_CR18","doi-asserted-by":"crossref","unstructured":"Raviteja Vemulapalli, Oncel Tuzel, Ming-Yu Liu et al (2016) Gaussian conditional random field network for semantic segmentation. In: IEEE Conf. On Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, Jun. 26-Jul.1, pp 3224\u20133233","DOI":"10.1109\/CVPR.2016.351"},{"key":"16230_CR19","doi-asserted-by":"crossref","unstructured":"Li X, Meng L, Tan Y et al (2021) Deep semantic segmentation-based multiple description coding. Multimedia Tools Appl 80(7):10323\u201310337","DOI":"10.1007\/s11042-020-09283-w"},{"key":"16230_CR20","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":"16230_CR21","unstructured":"Gao S, Cheng M M, Zhao K et al (2019) Res2net: A new multi-scale backbone architecture. IEEE Trans Pattern Anal Mach Intell"},{"key":"16230_CR22","unstructured":"Chen LC, Papandreou G, Kokkinos I et al (2014) Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv:1412.7062"},{"key":"16230_CR23","doi-asserted-by":"crossref","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","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"16230_CR24","unstructured":"Chen LC, Papandreou G, Schroff F et al (2017) Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587"},{"key":"16230_CR25","doi-asserted-by":"crossref","unstructured":"Chen LC, Zhu Y, Papandreou G et al (2018) Encoder-decoder 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":"16230_CR26","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv: arXiv:1409.0473"},{"key":"16230_CR27","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"12","key":"16230_CR28","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. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"16230_CR29","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":"16230_CR30","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"16230_CR31","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 267\u2013283","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"16230_CR32","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. 2016: 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"16230_CR33","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A et al (2016) Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition. x: 2921\u20132929","DOI":"10.1109\/CVPR.2016.319"},{"issue":"2","key":"16230_CR34","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CKI et al (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"key":"16230_CR35","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S et al (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"16230_CR36","doi-asserted-by":"crossref","unstructured":"Wu T, Huang J, Gao G et al (2021) Embedded discriminative attention mechanism for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 16765\u201316774","DOI":"10.1109\/CVPR46437.2021.01649"},{"key":"16230_CR37","doi-asserted-by":"crossref","unstructured":"Fan M, Lai S, Huang J et al (2021) Rethinking bisenet for real-time semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 9716\u20139725","DOI":"10.1109\/CVPR46437.2021.00959"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16230-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16230-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16230-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T13:15:46Z","timestamp":1712063746000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16230-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,2]]},"references-count":37,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["16230"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16230-y","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,9,2]]},"assertion":[{"value":"20 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}