{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:27:44Z","timestamp":1760171264626,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,1,9]],"date-time":"2022-01-09T00:00:00Z","timestamp":1641686400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,9]],"date-time":"2022-01-09T00:00:00Z","timestamp":1641686400000},"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":[[2022,1,9]]},"DOI":"10.1109\/sii52469.2022.9708836","type":"proceedings-article","created":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T15:08:41Z","timestamp":1646665721000},"page":"367-374","source":"Crossref","is-referenced-by-count":10,"title":["A Multimodal Learning-from-Observation Towards All-at-once Robot Teaching using Task Cohesion"],"prefix":"10.1109","author":[{"given":"Iori","family":"Yanaokura","sequence":"first","affiliation":[{"name":"University of Tokyo,Department of MechanoInformatics,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoki","family":"Wake","sequence":"additional","affiliation":[{"name":"Microsoft,Applied Robotics Research,Redmond,WA,USA,98052"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Sasabuchi","sequence":"additional","affiliation":[{"name":"Microsoft,Applied Robotics Research,Redmond,WA,USA,98052"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Riku","family":"Arakawa","sequence":"additional","affiliation":[{"name":"Microsoft,Applied Robotics Research,Redmond,WA,USA,98052"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kei","family":"Okada","sequence":"additional","affiliation":[{"name":"University of Tokyo,Department of MechanoInformatics,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Takamatsu","sequence":"additional","affiliation":[{"name":"Microsoft,Applied Robotics Research,Redmond,WA,USA,98052"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masayuki","family":"Inaba","sequence":"additional","affiliation":[{"name":"University of Tokyo,Department of MechanoInformatics,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katsushi","family":"Ikeuchi","sequence":"additional","affiliation":[{"name":"Microsoft,Applied Robotics Research,Redmond,WA,USA,98052"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","first-page":"1","article-title":"Human grasping database for activities of daily living with depth, color and kinematic data streams","volume":"5","author":"saudabayev","year":"2018","journal-title":"Scientific Data"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2859041"},{"key":"ref10","first-page":"1547","article-title":"Learning attractor landscapes for learning motor primitives","author":"ijspeert","year":"2003","journal-title":"NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-011-9234-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/70.294211"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989466"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460857"},{"article-title":"V2cnet: A deep learning framework to translate videos to commands for robotic manipulation","year":"2019","author":"nguyen","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139462"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v25i1.7979","article-title":"Understanding natural language commands for robotic navigation and mobile manipulation","volume":"25","author":"tellex","year":"2011","journal-title":"AAAI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3044029"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2004.1301641"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/tee.23008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/70.338535"},{"year":"0","key":"ref27","article-title":"Speech to text — microsoft azure"},{"article-title":"Semantic constraints to represent common sense required in household actions for multi-modal learning-from-observation robot","year":"2021","author":"ikeuchi","key":"ref3"},{"key":"ref6","first-page":"1","article-title":"A survey grasping database for activities of daily living with depth, color and of robot learning from demonstration","volume":"5","author":"argall","year":"2018","journal-title":"Robotics and Autonomous kinematic data streams \" Scientific data"},{"year":"0","key":"ref29","article-title":"Azure kinect dk – develop ai models — microsoft azure"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1007\/s11263-018-1123-1","article-title":"Describing upper-body motions based on labanotation for learning-fromo-bservation robots","volume":"126","author":"ikeuchi","year":"2018","journal-title":"IJCV"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907261"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref2","article-title":"Verbal focus-of-attention system for learning-from-demonstration","author":"wake","year":"2021","journal-title":"ICRA"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157815"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF49454.2021.9382750"},{"key":"ref20","first-page":"957","article-title":"From word embeddings to document distances","author":"kusner","year":"2015","journal-title":"ICML"},{"key":"ref22","article-title":"Grasp-type recognition leveraging object affordance","author":"wake","year":"2020","journal-title":"HOBI–RO-MAN Workshop"},{"key":"ref21","first-page":"104","article-title":"Minsky’s frame system theory","author":"minsky","year":"1975","journal-title":"Proceedings of the 1975 Workshop on Theoretical Issues in Natural Language Processing TINLAP ’75"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487305"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"article-title":"Cuhk & ethz & siat submission to activitynet challenge 2016","year":"2016","author":"xiong","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"}],"event":{"name":"2022 IEEE\/SICE International Symposium on System Integration (SII)","start":{"date-parts":[[2022,1,9]]},"location":"Narvik, Norway","end":{"date-parts":[[2022,1,12]]}},"container-title":["2022 IEEE\/SICE International Symposium on System Integration (SII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9708598\/9708599\/09708836.pdf?arnumber=9708836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T21:13:00Z","timestamp":1670361180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9708836\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,9]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/sii52469.2022.9708836","relation":{},"subject":[],"published":{"date-parts":[[2022,1,9]]}}}