{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T12:43:00Z","timestamp":1763642580411,"version":"3.41.2"},"reference-count":38,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2019,3,14]],"date-time":"2019-03-14T00:00:00Z","timestamp":1552521600000},"content-version":"vor","delay-in-days":72,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61503271","61603267"],"award-info":[{"award-number":["61503271","61603267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003398","name":"Shanxi Scholarship Council of China","doi-asserted-by":"publisher","award":["2015-045","2016-044"],"award-info":[{"award-number":["2015-045","2016-044"]}],"id":[{"id":"10.13039\/501100003398","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004480","name":"Natural Science Foundation of Shanxi Province","doi-asserted-by":"publisher","award":["201801D121144","201801D221190"],"award-info":[{"award-number":["201801D121144","201801D221190"]}],"id":[{"id":"10.13039\/501100004480","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Complexity"],"published-print":{"date-parts":[[2019,1]]},"abstract":"<jats:p>The task of semantic segmentation is to obtain strong pixel\u2010level annotations for each pixel in the image. For fully supervised semantic segmentation, the task is achieved by a segmentation model trained using pixel\u2010level annotations. However, the pixel\u2010level annotation process is very expensive and time\u2010consuming. To reduce the cost, the paper proposes a semantic candidate regions trained extreme learning machine (ELM) method with image\u2010level labels to achieve pixel\u2010level labels mapping. In this work, the paper casts the pixel mapping problem into a candidate region semantic inference problem. Specifically, after segmenting each image into a set of superpixels, superpixels are automatically combined to achieve segmentation of candidate region according to the number of image\u2010level labels. Semantic inference of candidate regions is realized based on the relationship and neighborhood rough set associated with semantic labels. Finally, the paper trains the ELM using the candidate regions of the inferred labels to classify the test candidate regions. The experiment is verified on the MSRC dataset and PASCAL VOC 2012, which are popularly used in semantic segmentation. The experimental results show that the proposed method outperforms several state\u2010of\u2010the\u2010art approaches for deep semantic segmentation.<\/jats:p>","DOI":"10.1155\/2019\/9180391","type":"journal-article","created":{"date-parts":[[2019,3,14]],"date-time":"2019-03-14T23:33:41Z","timestamp":1552606421000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions"],"prefix":"10.1155","volume":"2019","author":[{"given":"Xinying","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guiqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5769-0565","authenticated-orcid":false,"given":"Gang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6116-3194","authenticated-orcid":false,"given":"Jinchang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinlin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2019,3,14]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2645157"},{"key":"e_1_2_9_2_2","first-page":"191","article-title":"Image semantic analysis and understanding: a review","volume":"2","author":"Gao J.","year":"2010","journal-title":"Pattern recognition and artificial intelligence"},{"key":"e_1_2_9_3_2","doi-asserted-by":"crossref","unstructured":"NohH. HongS. andHanB. Learning deconvolution network for semantic segmentation Proceedings of the IEEE International Conference on Computer Vision ICCV 2015 December 2015 Santiago Chile 1520\u20131528 https:\/\/doi.org\/10.1109\/ICCV.2015.178 2-s2.0-84973879016.","DOI":"10.1109\/ICCV.2015.178"},{"key":"e_1_2_9_4_2","doi-asserted-by":"crossref","unstructured":"LongJ. ShelhamerE. andDarrellT. Fully convolutional networks for semantic segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition CVPR 2015 June 2015 Boston Mass USA 3431\u20133440 2-s2.0-84959205572.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_9_5_2","doi-asserted-by":"crossref","unstructured":"PapandreouG. ChenL. MurphyK. P.et al. Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation Proceedings of the IEEE International Conference on Computer Vision (ICCV 2015) December 2015 Santiago Chile 1742\u20131750 https:\/\/doi.org\/10.1109\/ICCV.2015.203.","DOI":"10.1109\/ICCV.2015.203"},{"key":"e_1_2_9_6_2","doi-asserted-by":"crossref","unstructured":"LinD. DaiJ. JiaJ.et al. Scribblesup: scribble-supervised convolutional networks for semantic segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition CVPR 2016 July 2016 Las Vegas Nev USA 3159\u20133167 2-s2.0-84986265730.","DOI":"10.1109\/CVPR.2016.344"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2552172"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"VezhnevetsA.andBuhmannJ. M. Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR 2010 June 2010 San Francisco Calif USA 3249\u20133256 2-s2.0-77955986468.","DOI":"10.1109\/CVPR.2010.5540060"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2018.06.014"},{"key":"e_1_2_9_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.02.004"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.01.055"},{"key":"e_1_2_9_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2815946"},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882155"},{"key":"e_1_2_9_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2696747"},{"key":"e_1_2_9_15_2","doi-asserted-by":"crossref","unstructured":"WeiY. XiaoH. ShiH.et al. Revisiting dilated convolution: a simple approach for weakly- and semi-supervised semantic segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2018 June 2018 Salt Lake City Utah USA 7268\u20137277 https:\/\/doi.org\/10.1109\/CVPR.2018.00759.","DOI":"10.1109\/CVPR.2018.00759"},{"key":"e_1_2_9_16_2","doi-asserted-by":"crossref","unstructured":"LiuY. LiuJ. LiZ.et al. Weakly-supervised dual clustering for image semantic segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2013 Portland Ore USA 2075\u20132082 https:\/\/doi.org\/10.1109\/CVPR.2013.270.","DOI":"10.1109\/CVPR.2013.270"},{"key":"e_1_2_9_17_2","doi-asserted-by":"crossref","unstructured":"VezhnevetsA. FerrariV. andBuhmannJ. M. Weakly supervised semantic segmentation with a multi-image model Proceedings of the IEEE International Conference on Computer Vision ICCV 2011 November 2011 Barcelona Spain 643\u2013650.","DOI":"10.1109\/ICCV.2011.6126299"},{"key":"e_1_2_9_18_2","unstructured":"ZhangK. ZhangW. ZhengY.et al. Sparse reconstruction for weakly supervised semantic segmentation Proceedings of the International Joint Conference on Artificial Intelligence IJCAI 2013 August 2013 Beijing China 1889\u20131895 2-s2.0-84896063076."},{"key":"e_1_2_9_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2636150"},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"PathakD. KrahenbuhlP. andDarrellT. Constrained convolutional neural networks for weakly supervised segmentation Proceedings of the 15th IEEE International Conference on Computer Vision ICCV 2015 December 2015 Chile 1796\u20131804 2-s2.0-84973922870.","DOI":"10.1109\/ICCV.2015.209"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"PinheiroP. O.andCollobertR. From image-level to pixel-level labeling with convolutional networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2015 Boston Mass USA 1713\u20131721 https:\/\/doi.org\/10.1109\/CVPR.2015.7298780.","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"WeiY. FengJ. LiangX. ChengM.-M. ZhaoY. andYanS. Object region mining with adversarial erasing: a simple classification to semantic segmentation approach Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition CVPR 2017 July 2017 Hawaii USA 2-s2.0-85028502852.","DOI":"10.1109\/CVPR.2017.687"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.01.015"},{"key":"e_1_2_9_24_2","doi-asserted-by":"crossref","unstructured":"VezhnevetsA. FerrariV. andBuhmannJ. M. Weakly supervised structured output learning for semantic segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition CVPR 2012 June 2012 Providence RI USA 845\u2013852 2-s2.0-84866684103.","DOI":"10.1109\/CVPR.2012.6247757"},{"key":"e_1_2_9_25_2","doi-asserted-by":"crossref","unstructured":"OquabM. BottouL. LaptevI. andSivicJ. Learning and transferring mid-level image representations using convolutional neural networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR \u203214) June 2014 Columbus Ohio USA IEEE 1717\u20131724 https:\/\/doi.org\/10.1109\/cvpr.2014.222 2-s2.0-84911449395.","DOI":"10.1109\/CVPR.2014.222"},{"key":"e_1_2_9_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2835143"},{"key":"e_1_2_9_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"e_1_2_9_28_2","doi-asserted-by":"publisher","DOI":"10.3724\/SP.J.1001.2008.00640"},{"key":"e_1_2_9_29_2","doi-asserted-by":"crossref","unstructured":"HuangG. B. ZhuQ. Y. andSiewC. K. Extreme learning machine: a new learning scheme of feedforward neural networks 2 Proceedings of the IEEE International Joint Conference March 2004 Budapest Hungary 985\u2013990 2-s2.0-10944272650.","DOI":"10.1109\/IJCNN.2004.1380068"},{"key":"e_1_2_9_30_2","doi-asserted-by":"crossref","unstructured":"ShottonJ. WinnJ. RotherC.et al. Textonboost: joint appearance shape and context modeling for multi-class object recognition and segmentation 3951 Proceedings of the European Conference on Computer Vision ECCV 2006 May 2006 Graz Austria.","DOI":"10.1007\/11744023_1"},{"key":"e_1_2_9_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"HariharanB. Arbel\u00e1ezP. BourdevL. MajiS. andMalikJ. Semantic contours from inverse detectors Proceedings of the IEEE International Conference on Computer Vision ICCV 2011 November 2011 Barcelona Spain 991\u2013998 https:\/\/doi.org\/10.1109\/ICCV.2011.6126343 2-s2.0-84856686500.","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"e_1_2_9_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.01.076"},{"key":"e_1_2_9_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2014.2381471"},{"key":"e_1_2_9_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-017-9529-6"},{"key":"e_1_2_9_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2641986"},{"key":"e_1_2_9_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.02.005"},{"key":"e_1_2_9_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2900509"}],"container-title":["Complexity"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2019\/9180391.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2019\/9180391.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2019\/9180391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T11:46:49Z","timestamp":1723031209000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2019\/9180391"}},"subtitle":[],"editor":[{"given":"Jungong","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,1]]}},"alternative-id":["10.1155\/2019\/9180391"],"URL":"https:\/\/doi.org\/10.1155\/2019\/9180391","archive":["Portico"],"relation":{},"ISSN":["1076-2787","1099-0526"],"issn-type":[{"type":"print","value":"1076-2787"},{"type":"electronic","value":"1099-0526"}],"subject":[],"published":{"date-parts":[[2019,1]]},"assertion":[{"value":"2018-11-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-02-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-03-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"9180391"}}