{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T20:32:18Z","timestamp":1725741138833},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/case48305.2020.9216770","type":"proceedings-article","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T16:01:51Z","timestamp":1602172911000},"page":"1447-1452","source":"Crossref","is-referenced-by-count":3,"title":["Bridging Visual Perception with Contextual Semantics for Understanding Robot Manipulation Tasks"],"prefix":"10.1109","author":[{"given":"Chen","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Jagersand","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"V2cnet: A deep learning framework to translate videos to commands for robotic manipulation","author":"nguyen","year":"2019","journal-title":"arXiv preprint arXiv 1903 11593"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968278"},{"key":"ref12","article-title":"Understanding contexts inside robot and human manipulation tasks through a vision-language model and ontology system in a video stream","author":"jiang","year":"2020","journal-title":"arXiv preprint arXiv 2003 01163"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2010.2076404"},{"key":"ref15","first-page":"714","article-title":"Grounding robot plans from natural language instructions with incomplete world knowledge","author":"nyga","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref16","first-page":"381","article-title":"An ontology for failure interpretation in automated planning and execution","author":"diab","year":"2019","journal-title":"Iberian Robotics Conference"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967667"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943279"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2019.8843293"},{"key":"ref4","first-page":"1684","article-title":"Owl-enabled assembly planning for robotic agents","author":"be\u00dfler","year":"2018","journal-title":"Int Conf Auton Agents Multiagent syst International Foundation for Autonomous Agents and Multiagent Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460857"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967754"},{"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":"Twenty-Ninth AAAI Conference on Artificial Intelligence"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2014.7041483"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.12.004"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1066"},{"key":"ref9","article-title":"Learning collaborative action plans from youtube videos","author":"zhang","year":"2019","journal-title":"Proceedings of the International Symposium on Robotics Research (ISRR 2019)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907656"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2757001.2757003"},{"key":"ref21","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"NIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2017.07.002"},{"key":"ref23","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv preprint arXiv 1504 00325"}],"event":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2020,8,20]]},"location":"Hong Kong, Hong Kong","end":{"date-parts":[[2020,8,21]]}},"container-title":["2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9210430\/9216730\/09216770.pdf?arnumber=9216770","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T12:59:35Z","timestamp":1669121975000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9216770\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/case48305.2020.9216770","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}