{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T16:48:38Z","timestamp":1790786918400,"version":"4.1.0"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,5]]},"DOI":"10.1109\/icra.2016.7487176","type":"proceedings-article","created":{"date-parts":[[2016,6,9]],"date-time":"2016-06-09T17:33:24Z","timestamp":1465493604000},"page":"536-543","source":"Crossref","is-referenced-by-count":195,"title":["Deep learning for tactile understanding from visual and haptic data"],"prefix":"10.1109","author":[{"given":"Yang","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa Anne","family":"Hendricks","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katherine J.","family":"Kuchenbecker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Going deeper with convolutions","author":"szegedy","year":"2014","journal-title":"arXiv preprint arXiv 1409 4842"},{"key":"ref32","article-title":"Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation","author":"powers","year":"2011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2495\/D&N-V1-N1-48-60"},{"key":"ref30","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref37","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jphysparis.2004.03.006"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1163\/156855308X314533"},{"key":"ref34","article-title":"Grammar as a foreign language","author":"vinyals","year":"2014","journal-title":"arXiv preprint arXiv 1412 7449"},{"key":"ref10","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2013","journal-title":"arXiv preprint arXiv 1310 1531"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2008.571"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2012.00004"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref14","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref15","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning (ICML-14)"},{"key":"ref16","first-page":"577","article-title":"Unconstrained on-line handwriting recognition with recurrent neural networks","author":"graves","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2011.2157504"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/978-3-319-10584-0_23","article-title":"Learning rich features from rgb-d images for object detection and segmentation","author":"gupta","year":"2014","journal-title":"Computer Vision-ECCV 2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref28","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"11 Th Annual Conference of the International Speech Communication Association INTERSPEECH-2010"},{"key":"ref4","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s00221-005-2396-5"},{"key":"ref6","article-title":"Toward a large-scale visuo-haptic dataset for robotic learning","author":"burka","year":"2015","journal-title":"proceedings of the Workshop on the Future of Datasets in Vision at Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570499"},{"key":"ref5","article-title":"Material recognition in the wild with the materials in context database","author":"bell","year":"2014","journal-title":"arXiv preprint arXiv 1412 0623"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631000"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2014.09.021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_22"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Computer Vision and Pattern Recognition 2009 CVPR 2009 IEEE Conference on"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","article-title":"Emonets: Multimodal deep learning approaches for emotion recognition in video","author":"kahou","year":"2015","journal-title":"arXiv preprint arXiv 1503"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2621"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref23","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":"ref26","article-title":"Fully convolutional networks for semantic segmentation","author":"long","year":"2014","journal-title":"arXiv preprint arXiv 1411 4038"},{"key":"ref25","first-page":"13","article-title":"Instrumental and sensory evaluation of the frictional response of the skin following a single application of five moisturizing creams","volume":"43","author":"lod\u00e9n","year":"1992","journal-title":"J Soc Cosmet Chem"}],"event":{"name":"2016 IEEE International Conference on Robotics and Automation (ICRA)","location":"Stockholm, Sweden","start":{"date-parts":[[2016,5,16]]},"end":{"date-parts":[[2016,5,21]]}},"container-title":["2016 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7478842\/7487087\/07487176.pdf?arnumber=7487176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,9]],"date-time":"2019-09-09T09:23:07Z","timestamp":1568020987000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7487176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icra.2016.7487176","relation":{},"subject":[],"published":{"date-parts":[[2016,5]]}}}