{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T07:22:09Z","timestamp":1770276129161,"version":"3.49.0"},"reference-count":36,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2019,7,15]],"date-time":"2019-07-15T00:00:00Z","timestamp":1563148800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2019,9,9]]},"abstract":"<jats:p>Deep convolutional neural networks (CNNs) have shown outstanding performance in salient object detection. However, there exist two conundrums under-explored. 1) High-level features are beneficial to locate salient objects while low-level features contain fine-grained details. How to combine these two types of features to promote accuracy is the first conundrum. 2) Previous CNN-based methods adopt a convolutional layer after extracting features to infer saliency maps. While encountering images that are different greatly from training dataset, adopting a convolutional layer as a classifier is not robust enough to detect all salient objects. In addition, limited receptive field and lack of spatial correlation will cause salient objects to be incomplete while blurring their boundaries. In this paper, a Lateral Hierarchically Refining Network (LHRNet) is put forward for accurate salient object detection. Firstly, LHRNet efficiently integrates multi-level features, which simultaneously incorporates coarse semantics and fine details. Then a coarse saliency prediction is made from low-resolution features by convolution. Finally, a series of nearest neighbor classifiers are learned to hierarchically restore the missing parts of salient objects while refining their boundaries, yielding a more reliable final prediction. Comprehensive experiments demonstrate that this network performs favorably against state-of-the-art approaches on six datasets.<\/jats:p>","DOI":"10.3233\/jifs-182769","type":"journal-article","created":{"date-parts":[[2019,7,16]],"date-time":"2019-07-16T11:29:50Z","timestamp":1563276590000},"page":"2503-2514","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":3,"title":["LHRNet: Lateral hierarchically refining network for salient object detection"],"prefix":"10.1177","volume":"37","author":[{"given":"Tao","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"}]},{"given":"Jiaxu","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"}]}],"member":"179","published-online":{"date-parts":[[2019,7,15]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"3183","article-title":"Deep networks for saliency detection via local estimation and global search","author":"Wang L.","year":"2015","unstructured":"WangL., LuH. and RuanX., Deep networks for saliency detection via local estimation and global search, IEEE Conference on Computer Vision and Pattern Recognition (2015), 3183\u20133192.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_3_2","first-page":"5455","article-title":"Visual saliency based on multiscale deep features","author":"Li G.","year":"2015","unstructured":"LiG. and YuY., Visual saliency based on multiscale deep features, IEEE Conference on Computer Vision and Pattern Recognition (2015), 5455\u20135463.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_4_2","first-page":"1265","article-title":"Saliency detection by multicontext deep learning","author":"Zhao R.","year":"2015","unstructured":"ZhaoR., OuyangW. and LiH., Saliency detection by multicontext deep learning, IEEE Conference on Computer Vision and Pattern Recognition (2015), 1265\u20131274.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_5_2","first-page":"660","article-title":"Deep saliency with encoded low level distance map and high level features","author":"Lee G.","year":"2016","unstructured":"LeeG., TaiW.Y. and KimJ., Deep saliency with encoded low level distance map and high level features, IEEE Conference on Computer Vision and Pattern Recognition (2016), 660\u2013668.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_6_2","first-page":"678","article-title":"Dhsnet: Deep hierarchical saliency network for salient object detection","author":"Liu N.","year":"2016","unstructured":"LiuN. and HanJ., Dhsnet: Deep hierarchical saliency network for salient object detection, IEEE Conference on Computer Vision and Pattern Recognition (2016), 678\u2013686.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_7_2","first-page":"478","article-title":"Deep contrast learning for salient object detection","author":"Li G.","year":"2016","unstructured":"LiG. and YuY., Deep contrast learning for salient object detection, IEEE Conference on Computer Vision and Pattern Recognition (2016), 478\u2013487.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_8_2","first-page":"825","article-title":"Saliency detection with recurrent fully convolutional networks","author":"Wang L.","year":"2016","unstructured":"WangL., WangL. and LuH., Saliency detection with recurrent fully convolutional networks, European Conference on Computer Vision, Springer, Cham (2016), 825\u2013841.","journal-title":"European Conference on Computer Vision, Springer, Cham"},{"key":"e_1_3_2_9_2","first-page":"202","article-title":"Amulet: Aggregating multi-level convolutional features for salient object detection","author":"Zhang P.","year":"2017","unstructured":"ZhangP., WangD. and LuH., Amulet: Aggregating multi-level convolutional features for salient object detection, IEEE International Conference on Computer Vision (2017), 202\u2013211.","journal-title":"IEEE International Conference on Computer Vision"},{"key":"e_1_3_2_10_2","first-page":"1741","article-title":"A Bi-Directional Message Passing Model for Salient Object Detection","author":"Zhang L.","year":"2018","unstructured":"ZhangL., DaiJ. and LuH., A Bi-Directional Message Passing Model for Salient Object Detection, IEEE Conference on Computer Vision and Pattern Recognition (2018), 1741\u20131750.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_11_2","first-page":"109","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","author":"K P.","year":"2011","unstructured":"KP. and KoltunV., Efficient inference in fully connected crfs with gaussian edge potentials, Advances in Neural Information Processing Systems (2011), 109\u2013117.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"6","key":"e_1_3_2_12_2","first-page":"7","article-title":"Non-local Deep Features for Salient Object Detection","volume":"2","author":"Luo Z.","year":"2017","unstructured":"LuoZ., MishraK.A. and AchkarA., Non-local Deep Features for Salient Object Detection, CVPR 2(6) (2017), 7.","journal-title":"CVPR"},{"key":"e_1_3_2_13_2","first-page":"1644","article-title":"Learning to Promote Saliency Detectors","author":"Zeng Y.","year":"2018","unstructured":"ZengY., LuH. and ZhangL., Learning to Promote Saliency Detectors, IEEE Conference on Computer Vision and Pattern Recognition (2018), 1644\u20131653.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_14_2","first-page":"5300","article-title":"Deeply supervised salient object detection with short connections","author":"Hou Q.","year":"2017","unstructured":"HouQ., ChengM.M. and HuX., Deeply supervised salient object detection with short connections, IEEE Conference on Computer Vision and Pattern Recognition (2017), 5300\u20135309.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_15_2","first-page":"3089","article-title":"PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection","author":"Liu N.","year":"2018","unstructured":"LiuN., HanJ. and YangH.M., PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection, IEEE Conference on Computer Vision and Pattern Recognition (2018), 3089\u20133098.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_16_2","first-page":"4019","article-title":"A stagewise refinement model for detecting salient objects in images","author":"Wang T.","year":"2017","unstructured":"WangT., BorjiA. and ZhangL., A stagewise refinement model for detecting salient objects in images, IEEE International Conference on Computer Vision (2017), 4019\u20134028.","journal-title":"IEEE International Conference on Computer Vision"},{"key":"e_1_3_2_17_2","first-page":"212","article-title":"Learning uncertain convolutional features for accurate saliency detection","author":"Zhang P.","year":"2017","unstructured":"ZhangP., WangD. and LuH., Learning uncertain convolutional features for accurate saliency detection, ICCV) (2017), 212\u2013221.","journal-title":"ICCV)"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-162254"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2030969"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.3233\/IFS-2002-00150"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2636150"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.3233\/IFS-2011-0477"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.40"},{"key":"e_1_3_2_24_2","first-page":"2814","article-title":"Saliency optimization from robust background detection","author":"Zhu W.","year":"2014","unstructured":"ZhuW., LiangS. and WeiY., Saliency optimization from robust background detection, IEEE conference on computer vision and pattern recognition (2014), 2814\u20132821.","journal-title":"IEEE conference on computer vision and pattern recognition"},{"key":"e_1_3_2_25_2","first-page":"3166","article-title":"Saliency detection via graphbased manifold ranking","author":"Yang C.","year":"2013","unstructured":"YangC., ZhangL. and LuH., Saliency detection via graphbased manifold ranking, IEEE conference on computer vision and pattern recognition (2013), 3166\u20133173.","journal-title":"IEEE conference on computer vision and pattern recognition"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"e_1_3_2_28_2","first-page":"535","article-title":"Grab: Visual saliency via novel graph model and background priors","author":"Wang Q.","year":"2016","unstructured":"WangQ., ZhengW. and PiramuthuR., Grab: Visual saliency via novel graph model and background priors, IEEE Conference on Computer Vision and Pattern Recognition (2016), 535\u2013543.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_29_2","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long J.","year":"2015","unstructured":"LongJ., ShelhamerE. and DarrellT., Fully convolutional networks for semantic segmentation, IEEE conference on computer vision and pattern recognition (2015), 3431\u20133440.","journal-title":"IEEE conference on computer vision and pattern recognition"},{"issue":"2","key":"e_1_3_2_30_2","first-page":"4","article-title":"Feature Pyramid Networks for Object Detection","volume":"1","author":"Lin Y.T.","year":"2017","unstructured":"LinY.T., DollarP. and GirshickB.R., Feature Pyramid Networks for Object Detection, CVPR 1(2) (2017), 4.","journal-title":"CVPR"},{"key":"e_1_3_2_31_2","first-page":"109","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","author":"Kr P.","year":"2011","unstructured":"KrP. and KoltunV., Efficient inference in fully connected crfs with gaussian edge potentials, Advances in neural information processing systems (2011), 109\u2013117.","journal-title":"Advances in neural information processing systems"},{"key":"e_1_3_2_32_2","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy C.","year":"2015","unstructured":"SzegedyC., LiuW. and JiaY., Going deeper with convolutions, IEEE conference on computer vision and pattern recognition (2015), 1\u20139.","journal-title":"IEEE conference on computer vision and pattern recognition"},{"key":"e_1_3_2_33_2","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy C.","year":"2016","unstructured":"SzegedyC., VanhouckeV. and IoffeS., Rethinking the inception architecture for computer vision, IEEE conference on computer vision and pattern recognition (2016), 2818\u20132826.","journal-title":"IEEE conference on computer vision and pattern recognition"},{"key":"e_1_3_2_34_2","first-page":"12","article-title":"Inception-v4, inceptionresnet and the impact of residual connections on learning","volume":"4","author":"Szegedy C.","year":"2017","unstructured":"SzegedyC., IoffeS.and VanhouckeV, Inception-v4, inceptionresnet and the impact of residual connections on learning, AAAI 4 (2017), 12.","journal-title":"AAAI"},{"key":"e_1_3_2_35_2","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu F.","year":"2015","unstructured":"YuF. and KoltunV., Multi-scale context aggregation by dilated convolutions, arXiv:1511.07122, 2015.","journal-title":"arXiv:1511.07122"},{"key":"e_1_3_2_36_2","article-title":"MEnet: A Metric Expression Network for Salient Object Segmentation","author":"Cai S.","year":"2018","unstructured":"CaiS., HuangJ. and ZengD., MEnet: A Metric Expression Network for Salient Object Segmentation, arXiv:1805.05638, 2018.","journal-title":"arXiv:1805.05638"},{"key":"e_1_3_2_37_2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan K.","year":"2014","unstructured":"SimonyanK. and ZissermanA., Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556, 2014.","journal-title":"arXiv:1409.1556"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-182769","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-182769","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-182769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:30:32Z","timestamp":1770229832000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-182769"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,15]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,9,9]]}},"alternative-id":["10.3233\/JIFS-182769"],"URL":"https:\/\/doi.org\/10.3233\/jifs-182769","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,15]]}}}