{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:41:07Z","timestamp":1782409267425,"version":"3.54.5"},"reference-count":109,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tpami.2020.3043781","type":"journal-article","created":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T22:03:26Z","timestamp":1607637806000},"page":"1-1","source":"Crossref","is-referenced-by-count":13,"title":["Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction"],"prefix":"10.1109","author":[{"given":"Dan","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaogang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88690-7_40"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref3","article-title":"Pushing the boundaries of boundary detection using deep learning,","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Kokkinos"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_35"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00389"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.25"},{"key":"ref9","first-page":"2204","article-title":"Recurrent models of visual attention,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Mnih"},{"key":"ref10","article-title":"Gates,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Minka"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.161"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref15","article-title":"Learning deep structured multi-scale features using attention-gated CRFs for contour prediction,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299067"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.622"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2874279"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298897"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.594"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_14"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00012"},{"key":"ref29","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation,","author":"Lee","year":"2019"},{"key":"ref30","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Eigen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref32","article-title":"Multi-scale context aggregation by dilated convolutions,","author":"Yu","year":"2016"},{"key":"ref33","article-title":"Ocnet: Object context network for scene parsing,","author":"Yuan","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref36","article-title":"Segnet: A deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling,","author":"Badrinarayanan","year":"2015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.162"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_33"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_15"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"ref45","article-title":"Geometry-aware video object detection for static cameras,","volume-title":"Proc. British Mach. Vis. Conf.","author":"Xu"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.451"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00902"},{"key":"ref48","article-title":"High-resolution representations for labeling pixels and regions,","author":"Sun","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1412.7062"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.144"},{"key":"ref52","article-title":"Multi-scale dense networks for resource efficient image classification,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang"},{"key":"ref53","article-title":"Graph attention networks,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298685"},{"key":"ref55","first-page":"577","article-title":"Attention-based models for speech recognition,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Chorowski"},{"key":"ref56","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention,","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref57","article-title":"Attention is all you need,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref59","article-title":"Gated boltzmann machine for recognition under occlusion,","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. Workshop Transfer LearnRich Generative Models","author":"Tang"},{"key":"ref60","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling,","author":"Chung","year":"2014"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2745563"},{"key":"ref62","article-title":"Conditional random fields for object recognition,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Quattoni"},{"key":"ref63","article-title":"Semi-markov conditional random fields for information extraction,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Sarawagi"},{"key":"ref64","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data,","volume-title":"Proc. 18th Int. Conf. Mach. Learn.","author":"Lafferty"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315232"},{"key":"ref66","article-title":"Efficient inference in fully connected CRFs with gaussian edge potentials,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Kr\u00e4henb\u00fchl"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-7934-5"},{"key":"ref68","first-page":"316","article-title":"CRF-CNN: Modeling structured information in human pose estimation,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00412"},{"key":"ref70","first-page":"1314","article-title":"Causality with gates,","volume-title":"Proc. 15th Int. Conf. Artif. Intell. Statist.","author":"Winn"},{"key":"ref71","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks,","volume-title":"Proc. Adv. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref72","article-title":"Very deep convolutional networks for large-scale image recognition,","author":"Simonyan","year":"2014"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/34.1000236"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.262"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.406"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537320"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.110"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.231"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2839602"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298782"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.34"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2377715"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.79"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00281"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00073"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_3"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00043"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.238"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00594"},{"key":"ref102","article-title":"Rethinking atrous convolution for semantic image segmentation,","author":"Chen","year":"2017"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_19"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299025"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.191"},{"key":"ref108","article-title":"Pixelnet: Representation of the pixels, by the pixels, and for the pixels,","author":"Bansal","year":"2017"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_11"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09290049.pdf?arnumber=9290049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:49:14Z","timestamp":1704840554000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9290049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":109,"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3043781","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}