{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:18:14Z","timestamp":1771467494287,"version":"3.50.1"},"reference-count":76,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/iccv.2019.00532","type":"proceedings-article","created":{"date-parts":[[2020,2,28]],"date-time":"2020-02-28T05:27:52Z","timestamp":1582867672000},"page":"5217-5227","source":"Crossref","is-referenced-by-count":113,"title":["SPGNet: Semantic Prediction Guidance for Scene Parsing"],"prefix":"10.1109","author":[{"given":"Bowen","family":"Cheng","sequence":"first","affiliation":[{"name":"UIUC"}]},{"given":"Liang-Chieh","family":"Chen","sequence":"additional","affiliation":[{"name":"Google Inc."}]},{"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[{"name":"UIUC"}]},{"given":"Yukun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Google Inc."}]},{"given":"Zilong","family":"Huang","sequence":"additional","affiliation":[{"name":"Huazhong Univ. of Science and Technology"}]},{"given":"Jinjun","family":"Xiong","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center"}]},{"given":"Thomas","family":"Huang","sequence":"additional","affiliation":[{"name":"UIUC"}]},{"given":"Wen-Mei","family":"Hwu","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}]},{"given":"Honghui","family":"Shi","sequence":"additional","affiliation":[{"name":"IBM"}]},{"given":"Uiuc","family":"Uiuc","sequence":"additional","affiliation":[{"name":"NA"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_17"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.224"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref76","article-title":"Le. Neural architecture search with reinforcement learning","author":"zoph","year":"2017","journal-title":"ICLRE"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref38","article-title":"Parsenet: Looking wider to see better","author":"liu","year":"2015","journal-title":"arXiv 1506 04579"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.684"},{"key":"ref32","article-title":"Rethinking on multi-stage networks for human pose estimation","author":"li","year":"2019","journal-title":"arXiv preprint arXiv 1901 00828"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_31"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.234"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01170-8"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.644"},{"key":"ref61","article-title":"Bridging category-level and instance-level semantic image segmentation","author":"wu","year":"2016","journal-title":"arXiv 1605 06885"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00106"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_44"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"ref65","article-title":"Deeperlab: Single-shot image parser","author":"yang","year":"2019","journal-title":"arXiv preprint arXiv 1902 05023"},{"key":"ref29","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.144"},{"key":"ref67","article-title":"Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation","author":"yao","year":"2012","journal-title":"CVPR"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00199"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.518"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-97177-8_28"},{"key":"ref21","article-title":"Multiscale conditional random fields for image labeling","author":"he","year":"2004","journal-title":"CVPR"},{"key":"ref24","article-title":"Gather-excite: Exploiting feature context in convolutional neural networks","author":"hu","year":"2018","journal-title":"NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref51","article-title":"Spg-net: Segmentation prediction and guidance network for image inpainting","author":"song","year":"2018","journal-title":"arXiv preprint arXiv 1805 03356"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.433"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref55","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-6642-x"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.386"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref40","article-title":"Associative embedding: End-to-end learning for joint detection and grouping","author":"newell","year":"2017","journal-title":"NIPS"},{"key":"ref11","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"ECCV"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref13","article-title":"A2-nets: Double attention networks","author":"chen","year":"2018","journal-title":"NIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2895460"},{"key":"ref4","article-title":"Loss maxpooling for semantic image segmentation","author":"bul\u00f2","year":"2017","journal-title":"CVPR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref6","article-title":"Searching for efficient multi-scale architectures for dense image prediction","author":"chen","year":"2018","journal-title":"NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref8","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"chen","year":"2017","journal-title":"IEEE TPAMI"},{"key":"ref7","article-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs","author":"chen","year":"2015","journal-title":"ICLRE"},{"key":"ref49","article-title":"Stacked u-nets: a no-frills approach to natural image segmentation","author":"shah","year":"2018","journal-title":"arXiv preprint arXiv 1804 10204"},{"key":"ref9","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv preprint arXiv 1706 05587"},{"key":"ref46","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"MICCAI"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.353"},{"key":"ref48","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2013","journal-title":"arXiv preprint arXiv 1312 6229"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00591"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref41","article-title":"Stacked hourglass networks for human pose estimation","author":"newell","year":"2016","journal-title":"ECCV"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.189"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298636"}],"event":{"name":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Seoul, Korea (South)","start":{"date-parts":[[2019,10,27]]},"end":{"date-parts":[[2019,11,2]]}},"container-title":["2019 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8972782\/9008105\/09008568.pdf?arnumber=9008568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:38:45Z","timestamp":1756154325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9008568\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/iccv.2019.00532","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}