{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:42:44Z","timestamp":1777491764381,"version":"3.51.4"},"reference-count":217,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61601266"],"award-info":[{"award-number":["61601266"]}],"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":["61801272"],"award-info":[{"award-number":["61801272"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2017M612306"],"award-info":[{"award-number":["2017M612306"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Teacher Development Support Program of Shandong University of Technology"},{"name":"Shandong Province-sponsored Overseas Study Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2907071","type":"journal-article","created":{"date-parts":[[2019,4,12]],"date-time":"2019-04-12T02:00:24Z","timestamp":1555034424000},"page":"43110-43136","source":"Crossref","is-referenced-by-count":51,"title":["RGB-D-Based Object Recognition Using Multimodal Convolutional Neural Networks: A Survey"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7273-7499","authenticated-orcid":false,"given":"Mingliang","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8023-0142","authenticated-orcid":false,"given":"Guofeng","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vijay","family":"John","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.05.007"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-018-1695-0"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref174","first-page":"1912","article-title":"3D ShapeNets: A deep representation for volumetric shapes","author":"wu","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx106"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.88"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-28650-9_4"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEA.2014.6931468"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.412"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3934\/mfc.2018008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.2200\/S00822ED1V01Y201712COV015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.10.006"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref36","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref35","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.013"},{"key":"ref181","first-page":"244","article-title":"Semantic labeling of 3D point clouds for indoor scenes","author":"koppula","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.79"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906903"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807990"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3375-5"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-015-1527-0"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2763441"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353385"},{"key":"ref186","first-page":"5068","article-title":"Hierarchical semantic parsing for object pose estimation in densely cluttered scenes","author":"li","year":"2016","journal-title":"Proc IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225188"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130298"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.038"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486573"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2015.23"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2872175"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/34.765655"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref26","first-page":"2115","article-title":"Hierarchical matching pursuit for image classification: Architecture and fast algorithms","author":"bo","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2709749"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2460697"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989162"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2015.2405316"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.6"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540137"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2168604"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.04.077"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.12.015"},{"key":"ref146","first-page":"656","article-title":"Convolutional-recursive deep learning for 3D object classification","author":"socher","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"ref148","first-page":"129","article-title":"Parsing natural scenes and natural language with recursive neural networks","author":"socher","year":"2011","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1117\/12.2292428"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2476658"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_9"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9_19"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2883673"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.24428"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2017.2692271"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.10.010"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353446"},{"key":"ref167","author":"faerman","year":"2018","journal-title":"Semi-supervised learning on graphs based on local label distributions"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.08.035"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.5121\/ijsc.2011.2404"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.5120\/17689-8652"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1113"},{"key":"ref162","first-page":"89","article-title":"Co-training and expansion: Towards bridging theory and practice","author":"balcan","year":"2005","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2010.11.003"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.072"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"ref3","author":"naseer","year":"2018","journal-title":"Indoor scene understanding in 2 5\/3D for autonomous agents A survey"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462922"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2747134"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1109\/TVCG.2018.2864491","article-title":"Labels on levels: Labeling of multi-scale multi-instance and crowded 3D biological environments","volume":"25","author":"kou?il","year":"2019","journal-title":"IEEE Trans Vis Comput Graphics"},{"key":"ref159","first-page":"4","article-title":"Semi-supervised learning literature survey","volume":"2","author":"zhu","year":"2006","journal-title":"Comput Sci Univ Wisconsin-Madison"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.02.017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2638453"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"ref46","first-page":"3345","article-title":"Semi-supervised multimodal deep learning for RGB-D object recognition","author":"cheng","year":"2016","journal-title":"Proc Intern Joint Conf Artificial Intel (IJCAI)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77842-6_4"},{"key":"ref48","author":"blum","year":"2005","journal-title":"Multi-Sensor Image Fusion and Its Applications"},{"key":"ref47","author":"sun","year":"2017","journal-title":"Weakly-supervised dcnn for rgb-d object recognition in real-world applications which lack large-scale annotated training data"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2872629"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2864920"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2476655"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.151"},{"key":"ref72","first-page":"5","article-title":"3D shape matching with 3D shape contexts","author":"k\u00f6rtgen","year":"2003","journal-title":"Proc 7th Central Eur Seminar Comput Graph"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980567"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15558-1_26"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980382"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4650967"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540108"},{"key":"ref78","first-page":"135","article-title":"Efficient match kernel between sets of features for visual recognition","author":"bo","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980377"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.12.006"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00990"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1134\/S1054661816010065"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2018.02.059"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.12928\/telkomnika.v12i4.388"},{"key":"ref65","doi-asserted-by":"crossref","first-page":"2270","DOI":"10.1109\/TPAMI.2014.2316828","article-title":"3D object recognition in cluttered scenes with local surface features: A survey","volume":"36","author":"guo","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref66","first-page":"1038","article-title":"A survey and technology trends of 3D features for object recognition","volume":"136","author":"hashimoto","year":"2016","journal-title":"IEEJ Trans Electron Inf Syst"},{"key":"ref67","first-page":"7","article-title":"3D descriptors for object and category recognition: A comparative evaluation","volume":"1","author":"alexandre","year":"2012","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst (IROS)"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3042064"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.141"},{"key":"ref198","author":"couprie","year":"2013","journal-title":"Indoor Semantic Segmentation Using Depth Information"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.109"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00092"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.229"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref196","author":"reed","year":"2016","journal-title":"Generative adversarial text to image synthesis"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386175"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CGIV.2013.11"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.09.030"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13536"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.476"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995719"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2721108"},{"key":"ref91","doi-asserted-by":"crossref","first-page":"1354","DOI":"10.1109\/TPAMI.2013.212","article-title":"Multiple kernel learning for visual object recognition: A review","volume":"36","author":"bucak","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2729882"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15567-3_43"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.09.027"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248087"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/1282280.1282340"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130385"},{"key":"ref84","first-page":"54","article-title":"Methods for similarity search on 3D databases","volume":"2","author":"heczko","year":"2002","journal-title":"Datenbank-Spektrum"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383198"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/2674396.2674432"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/2632856.2632947"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/0262-8856(92)90076-F"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/571647.571648"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.3390\/s17030451"},{"key":"ref88","first-page":"244","article-title":"Kernel descriptors for visual recognition","author":"bo","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"ref100","article-title":"Majority vote classifiers: Theory and applications","author":"james","year":"1998"},{"key":"ref209","author":"zhou","year":"2014","journal-title":"Object detectors emerge in deep scene cnns"},{"key":"ref203","author":"li","year":"2014","journal-title":"Highly efficient forward and backward propagation of convolutional neural networks for pixelwise classification"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2017.2767705"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00007"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.374"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2018.2866510"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700808"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref210","author":"szegedy","year":"2013","journal-title":"Intriguing properties of neural networks"},{"key":"ref212","first-page":"1","article-title":"Identifying unknown unknowns in the open world: Representations and policies for guided exploration","author":"lakkaraju","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref213","first-page":"1","article-title":"Examining CNN representations with respect to dataset bias","author":"zhang","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref214","first-page":"1","article-title":"Interpreting CNN knowledge via an explanatory graph","author":"zhang","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref215","first-page":"1","article-title":"Growing interpretable part graphs on ConvNets via multi-shot learning","author":"zhang","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00920"},{"key":"ref217","author":"wu","year":"2017","journal-title":"Towards interpretable R-CNN by unfolding latent structures"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.55"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"ref125","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1145\/2897824.2925974","article-title":"Let there be color!: Joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification","volume":"35","author":"iizuka","year":"2016","journal-title":"ACM Trans Graph"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/IPTA.2017.8310101"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-018-1559-x"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2812225"},{"key":"ref130","author":"wang","year":"2016","journal-title":"Correlated and individual multi-modal deep learning for RGB-D object recognition"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.02.008"},{"key":"ref134","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref131","author":"loghmani","year":"2018","journal-title":"Recurrent convolutional fusion for RGB-D object recognition"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEA.2015.7334080"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_22"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.936725"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065717500393"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2018.2826541"},{"key":"ref141","first-page":"1017","article-title":"ICA with reconstruction cost for efficient overcomplete feature learning","author":"le","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806374"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766842"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0777-6"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299107"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2886133"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2798799"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.25"},{"key":"ref108","first-page":"4913","article-title":"Beyond spatial pooling: Fine-grained representation learning in multiple domains","author":"li","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1177\/1729881417752820"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-014-0511-6"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.11.004"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.047"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-00065-7_27"},{"key":"ref111","volume":"1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2015.7371280"},{"key":"ref110","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574717000339"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463204"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.11.013"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2013.04.005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2783331"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.11.001"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.188"},{"key":"ref118","article-title":"Fine-tuning CNN image retrieval with no human annotation","author":"radenovi?","year":"0","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref117","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.006"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3374-6"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139363"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.134"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.03.017"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2784352"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487310"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.5220\/0006511501210128"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019538"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08683987.pdf?arnumber=8683987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T19:40:35Z","timestamp":1628624435000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":217,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2907071","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}