{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T18:18:56Z","timestamp":1769019536080,"version":"3.49.0"},"reference-count":59,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61773301"],"award-info":[{"award-number":["61773301"]}],"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":["61876140"],"award-info":[{"award-number":["61876140"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Postdoctoral Support Scheme for Innovative Talents","award":["BX20180236"],"award-info":[{"award-number":["BX20180236"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3011327","type":"journal-article","created":{"date-parts":[[2020,7,24]],"date-time":"2020-07-24T20:23:24Z","timestamp":1595622204000},"page":"2428-2441","source":"Crossref","is-referenced-by-count":34,"title":["Joint Cross-Modal and Unimodal Features for RGB-D Salient Object Detection"],"prefix":"10.1109","volume":"23","author":[{"given":"Nianchang","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2828-9905","authenticated-orcid":false,"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4361-956X","authenticated-orcid":false,"given":"Jungong","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025222"},{"key":"ref38","first-page":"1","article-title":"Squeeze-and-excitation networks","volume":"1","author":"hu","year":"2019"},{"key":"ref33","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref32","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913107"},{"key":"ref30","article-title":"Quality-aware multimodal saliency detection via deep reinforcement learning","author":"wang","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2930906"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298938"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.58"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.31"},{"key":"ref28","first-page":"3927","article-title":"Contrast prior and fluid pyramid integration for RGB-D salient object detection","author":"zhao","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2891104"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00042"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2280096"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0149-9"},{"key":"ref20","article-title":"Rethinking RGB-D salient object detection: Models, datasets, and large-scale benchmarks","author":"fan","year":"2019"},{"key":"ref22","article-title":"Introducing intel realsense lidar camera","author":"realsense","year":"2020"},{"key":"ref21","first-page":"1318","article-title":"Enhanced computer vision with microsoft kinect sensor: A review","volume":"43","author":"han","year":"2013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2761775"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2898508"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00322"},{"key":"ref50","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"0","journal-title":"Proc Artif Intell Statist"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1004-z"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref58","first-page":"1130","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"0","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref57","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref56","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"ref54","first-page":"454","article-title":"Leveraging stereopsis for saliency analysis","author":"niu","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref53","first-page":"92","article-title":"RGB-D salient object detection: A benchmark and algorithms","author":"peng","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref52","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.34"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2688136"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2823769"},{"key":"ref13","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751965"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2900908"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2859746"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.535"},{"key":"ref3","first-page":"597","article-title":"Online tracking by learning discriminative saliency map with convolutional neural network","author":"hong","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846598"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2693022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00330"},{"key":"ref49","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00187"},{"key":"ref46","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"chen","year":"2014"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00330"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.05.004"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2682981"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.323"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298731"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09147051.pdf?arnumber=9147051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:37Z","timestamp":1652194297000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9147051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3011327","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}