{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:53:50Z","timestamp":1761897230465,"version":"3.44.0"},"reference-count":36,"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\/iros40897.2019.8967621","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"6113-6119","source":"Crossref","is-referenced-by-count":3,"title":["An Object Attribute Guided Framework for Robot Learning Manipulations from Human Demonstration Videos"],"prefix":"10.1109","author":[{"given":"Qixiang","family":"Zhang","sequence":"first","affiliation":[{"name":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006"}]},{"given":"Junhong","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006"}]},{"given":"Dayong","family":"Liang","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006"}]},{"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"}]},{"given":"Xiaojing","family":"Zhou","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006"}]},{"given":"Zihan","family":"Ye","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006"}]},{"given":"Wenyin","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545639"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0851-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref34","article-title":"T-C3D: Temporal Convolutional 3D Network for Real-Time Action Recognition","author":"liu","year":"2018","journal-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.08.003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.04.015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759555"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989247"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref16","first-page":"67","article-title":"A cognitive system for understanding human manipulation actions","author":"yang","year":"2014","journal-title":"Advances in Cognitive Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.621"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"ref4","article-title":"One-shot visual imitation learning via meta-learning","author":"finn","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00151"},{"key":"ref3","article-title":"One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks","author":"yu","year":"2018","journal-title":"arXiv preprint arXiv 1810 10053"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00050"},{"key":"ref29","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on International Conference on Machine Learning (ICML)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157815"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9671","article-title":"Robot Learning Manipulation Action Plans by “Watching” Unconstrained Videos from the World Wide Web","author":"yang","year":"2015","journal-title":"The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206575"},{"key":"ref2","article-title":"One-shot imitation from observing humans via domain-adaptive metalearning","volume":"abs 1802","author":"yu","year":"2018","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911410459"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460857"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.172"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11212","article-title":"An end-to-end spatiotemporal attention model for human action recognition from skeleton data","author":"song","year":"2017","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984061"},{"key":"ref26","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2019,11,3]]},"location":"Macau, China","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\/08967621.pdf?arnumber=8967621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:07:53Z","timestamp":1757095673000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967621\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967621","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}