{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:35:59Z","timestamp":1771958159036,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8967961","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"3980-3987","source":"Crossref","is-referenced-by-count":28,"title":["Learning to Estimate Pose and Shape of Hand-Held Objects from RGB Images"],"prefix":"10.1109","author":[{"given":"Mia","family":"Kokic","sequence":"first","affiliation":[{"name":"Robotics, Perception, and Learning, EECS, KTH,Stockholm,Sweden"}]},{"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[{"name":"Robotics, Perception, and Learning, EECS, KTH,Stockholm,Sweden"}]},{"given":"Jeannette","family":"Bohg","sequence":"additional","affiliation":[{"name":"Stanford University,Computer Science Department,CA,USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2004.1371616"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref33","article-title":"Siamese neural networks for one-shot image recognition","volume":"2","author":"koch","year":"2015","journal-title":"ICML Deep Learning Workshop"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref31","article-title":"Basic Algebra I","author":"jacobson","year":"2009","journal-title":"ser Basic Algebra"},{"key":"ref30","author":"cederberg","year":"2013","journal-title":"A Course in Modern Geometries"},{"key":"ref37","article-title":"Augmented cyclegan: Learning many-to-many mappings from unpaired data","author":"almahairi","year":"2018","journal-title":"arXiv preprint arXiv 1802 10363"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152855"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref10","first-page":"1360","article-title":"A scalable approach for understanding the visual structures of hand grasps","author":"cai","year":"2015","journal-title":"2015 IEEE International Conference on Robotics and Automation (ICRA) IEEE"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1177\/0278364909105606"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298637"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354088"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TOH.2014.2326871"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.034"},{"key":"ref15","first-page":"524","volume":"47","author":"cai","year":"2017","journal-title":"An ego-vision system for hand grasp analysis"},{"key":"ref16","first-page":"7","article-title":"First-person hand action benchmark with rgb-d videos and 3d hand pose annotations","volume":"1","author":"garcia-hernando","year":"2017","journal-title":"arXiv preprint arXiv 1704 02463"},{"key":"ref17","first-page":"4004","article-title":"Deep metric learning via lifted structured feature embedding","author":"oh song","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.329"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.260"},{"key":"ref28","first-page":"682","article-title":"On pre-trained image features and synthetic images for deep learning","author":"hinterstoisser","year":"2018","journal-title":"European Conference on Computer Vision"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00319"},{"key":"ref3","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.525"},{"key":"ref29","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","author":"tremblay","year":"2018","journal-title":"arXiv preprint arXiv 1809 10790"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.443"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126483"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509753"},{"key":"ref2","article-title":"Global search with bernoulli alternation kernel for task-oriented grasping informed by simulation","author":"antonova","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2013.04.002"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8239542"},{"key":"ref20","first-page":"484","article-title":"Learning a predictable and generative vector representation for objects","author":"girdhar","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.169"},{"key":"ref21","article-title":"Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes","author":"xiang","year":"2017","journal-title":"arXiv preprint arXiv 1711 03890"},{"key":"ref24","first-page":"712","article-title":"Implicit 3d orientation learning for 6d object detection from rgb images","author":"sundermeyer","year":"2018","journal-title":"European Conference on Computer Vision"},{"key":"ref41","first-page":"548","article-title":"Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes","author":"hinterstoisser","year":"2012","journal-title":"Asian Conference on Computer Vision"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.366"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.16"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.416"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Macau, China","start":{"date-parts":[[2019,11,3]]},"end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08967961.pdf?arnumber=8967961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:24:03Z","timestamp":1755800643000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967961\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967961","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}