{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T08:17:28Z","timestamp":1775031448694,"version":"3.50.1"},"reference-count":91,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB2103402"],"award-info":[{"award-number":["2020YFB2103402"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSF, China","doi-asserted-by":"publisher","award":["61625301"],"award-info":[{"award-number":["61625301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSF, China","doi-asserted-by":"publisher","award":["61731018"],"award-info":[{"award-number":["61731018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Scientific Research Project of Zhejiang Lab","award":["2019KB0AC01"],"award-info":[{"award-number":["2019KB0AC01"]}]},{"name":"Major Scientific Research Project of Zhejiang Lab","award":["2019KB0AB02"],"award-info":[{"award-number":["2019KB0AB02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3099369","type":"journal-article","created":{"date-parts":[[2021,7,30]],"date-time":"2021-07-30T20:21:17Z","timestamp":1627676477000},"page":"7050-7063","source":"Crossref","is-referenced-by-count":19,"title":["Towards Efficient Scene Understanding via Squeeze Reasoning"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0550-8247","authenticated-orcid":false,"given":"Xiangtai","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xia","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ansheng","family":"You","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1428-8848","authenticated-orcid":false,"given":"Guangliang","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3063-2925","authenticated-orcid":false,"given":"Kuiyuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhai","family":"Tong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1493-7569","authenticated-orcid":false,"given":"Zhouchen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","first-page":"552","article-title":"ESPNet: Efficient spatial pyramid of dilated convolutions for semantic segmentation","author":"mehta","year":"2018","journal-title":"Proc ECCV"},{"key":"ref72","first-page":"1","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc NeurIPS Workshops"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00936"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00934"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00941"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00064"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2750080"},{"key":"ref38","first-page":"13065","article-title":"Squeeze-and-attention networks for semantic segmentation","author":"zhong","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref78","article-title":"Wider or deeper: Revisiting the ResNet model for visual recognition","author":"wu","year":"2016","journal-title":"arXiv 1611 10080"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"ref30","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00199"},{"key":"ref36","first-page":"6511","article-title":"Compact generalized non-local network","author":"yue","year":"2018","journal-title":"Proc NIPS"},{"key":"ref35","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc ECCV"},{"key":"ref34","article-title":"ParseNet: Looking wider to see better","author":"liu","year":"2015","journal-title":"arXiv 1506 04579"},{"key":"ref60","first-page":"405","article-title":"ICNet for real-time semantic segmentation on high-resolution images","author":"zhao","year":"2018","journal-title":"Proc ECCV"},{"key":"ref62","first-page":"775","article-title":"Semantic flow for fast and accurate scene parsing","author":"li","year":"2020","journal-title":"Proc ECCV"},{"key":"ref61","first-page":"325","article-title":"BiSeNet: Bilateral segmentation network for real-time semantic segmentation","author":"yu","year":"2018","journal-title":"Proc ECCV"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00975"},{"key":"ref28","first-page":"1","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"chen","year":"2015","journal-title":"Proc ICLR"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01289"},{"key":"ref27","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"Proc ICLR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.477"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00713"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00628"},{"key":"ref69","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc ICLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref22","article-title":"Semantic understanding of scenes through the ADE20K dataset","author":"zhou","year":"2016","journal-title":"arXiv 1608 05442"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"ref58","first-page":"8713","article-title":"Searching for efficient multi-scale architectures for dense image prediction","author":"chen","year":"2018","journal-title":"Proc NIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00690"},{"key":"ref56","first-page":"587","article-title":"Adaptive affinity fields for semantic segmentation","author":"ke","year":"2018","journal-title":"Proc ECCV"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00533"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00254"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6805"},{"key":"ref10","article-title":"CCNet: Criss-cross attention for semantic segmentation","author":"huang","year":"2018","journal-title":"arXiv 1811 11721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00068"},{"key":"ref40","article-title":"Dual attention network for scene segmentation","author":"fu","year":"2018","journal-title":"arXiv 1809 02983"},{"key":"ref12","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc ECCV"},{"key":"ref13","article-title":"OCNet: Object context network for scene parsing","author":"yuan","year":"2018","journal-title":"arXiv 1809 00916"},{"key":"ref14","article-title":"Segmentation transformer: Object-contextual representations for semantic segmentation","author":"yuan","year":"2019","journal-title":"arXiv 1909 11065"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00692"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00926"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.550"},{"key":"ref17","first-page":"379","article-title":"Representative graph neural network","author":"yu","year":"2020","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref84","first-page":"520","article-title":"Efficient uncertainty estimation for semantic segmentation in videos","author":"huang","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref18","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00929"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref89","author":"chen","year":"2018","journal-title":"mmdetection"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref6","first-page":"4905","article-title":"Understanding the effective receptive field in deep convolutional neural networks","author":"luo","year":"2016","journal-title":"Proc NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref85","first-page":"1853","article-title":"Symbolic graph reasoning meets convolutions","author":"liang","year":"2018","journal-title":"Proc NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00770"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00378"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00897"},{"key":"ref48","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc MICCAI"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.224"},{"key":"ref42","first-page":"267","article-title":"PSANet: Point-wise spatial attention network for scene parsing","author":"zhao","year":"2018","journal-title":"Proc ECCV"},{"key":"ref41","first-page":"352","article-title":"A²-nets: Double attention networks","author":"chen","year":"2018","journal-title":"Proc NIPS"},{"key":"ref44","first-page":"9225","article-title":"Beyond grids: Learning graph representations for visual recognition","author":"li","year":"2018","journal-title":"Proc NIPS"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/79.543975"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09502519.pdf?arnumber=9502519","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:11Z","timestamp":1652194211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9502519\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3099369","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}