{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T16:44:24Z","timestamp":1781541864794,"version":"3.54.5"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"State Key Development Program","award":["2018YFC0830103"],"award-info":[{"award-number":["2018YFC0830103"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702565"],"award-info":[{"award-number":["61702565"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672552"],"award-info":[{"award-number":["61672552"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"crossref","award":["2017B010116001"],"award-info":[{"award-number":["2017B010116001"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["18lgpy63"],"award-info":[{"award-number":["18lgpy63"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"GD-NSF","award":["2017A030312006"],"award-info":[{"award-number":["2017A030312006"]}]},{"name":"SenseTime Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1109\/tip.2018.2878956","type":"journal-article","created":{"date-parts":[[2018,10,31]],"date-time":"2018-10-31T19:11:50Z","timestamp":1541013110000},"page":"1591-1601","source":"Crossref","is-referenced-by-count":73,"title":["Cross-Modal Attentional Context Learning for RGB-D Object Detection"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yukang","family":"Gan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hejun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref38","first-page":"5455","article-title":"Visual saliency based on multiscale deep features","author":"li","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref33","author":"sharma","year":"2015","journal-title":"Action recognition using visual attention"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref31","first-page":"4507","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"14","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref30","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.94"},{"key":"ref36","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref28","author":"bahdanau","year":"2014","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2642789"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964322"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33885-4_60"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206532"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.107"},{"key":"ref21","first-page":"30","article-title":"Learning spatial context: Using stuff to find things","author":"heitz","year":"2008","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1666420.1666446"},{"key":"ref23","article-title":"Contrast-oriented deep neural networks for salient object detection","author":"li","year":"0","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref26","author":"chu","year":"2016","journal-title":"Deep feature based contextual model for object detection"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2772796"},{"key":"ref50","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.212"},{"key":"ref52","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139363"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2865036"},{"key":"ref12","first-page":"541","article-title":"LSTM-CF: Unifying context modeling and fusion with lstms for RGB-D scene labeling","author":"li","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095119"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980382"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225188"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995719"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225137"},{"key":"ref18","first-page":"350","article-title":"A statistical model for general contextual object recognition","author":"carbonetto","year":"2004","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2602079"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref7","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","first-page":"483","article-title":"Multi-stage contour based detection of deformable objects","author":"ravishankar","year":"2008","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353446"},{"key":"ref46","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD images","author":"silberman","year":"2012","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref48","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.34"},{"key":"ref44","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","author":"xu","year":"2015","journal-title":"Show attend and tell Neural image caption generation with visual attention"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8548629\/08517140.pdf?arnumber=8517140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:13:30Z","timestamp":1657746810000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8517140\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":52,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tip.2018.2878956","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4]]}}}