{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:12:44Z","timestamp":1775067164170,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/lra.2022.3193019","type":"journal-article","created":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T19:28:54Z","timestamp":1658431734000},"page":"10224-10231","source":"Crossref","is-referenced-by-count":19,"title":["Self-Supervised Reinforcement Learning for Active Object Detection"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3834-4795","authenticated-orcid":false,"given":"Fen","family":"Fang","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0278-2723","authenticated-orcid":false,"given":"Wenyu","family":"Liang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4644-0664","authenticated-orcid":false,"given":"Yan","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0105-5903","authenticated-orcid":false,"given":"Qianli","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4103-3824","authenticated-orcid":false,"given":"Joo-Hwee","family":"Lim","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00649"},{"key":"ref4","article-title":"Reinforcement learning with unsupervised auxiliary tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jaderberg","year":"2017"},{"key":"ref5","first-page":"7424","article-title":"Can increasing input dimensionality improve deep reinforcement learning?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ota","year":"2020"},{"key":"ref6","first-page":"5639","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srinivas","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2890849"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11798"},{"key":"ref11","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc.34th Int. Conf. Neural Inf. Process. Syst.","author":"Yu","year":"2020"},{"key":"ref12","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506078"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_4"},{"key":"ref15","article-title":"Online Q-learning using connectionist systems","author":"Rummery","year":"1994"},{"key":"ref16","first-page":"1597","article-title":"A simple framework for constrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812213"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref19","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Laskin","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.103"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989164"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190661"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561388"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref28","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schaul","year":"2016"},{"key":"ref29","article-title":"A framework for efficient robotic manipulation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Zhan","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2785233"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.011"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.260"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/e20050370"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.1999.791227"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/34.982896"},{"key":"ref36","first-page":"1718","article-title":"Bayesian active object recognition via Gaussian process regression","volume-title":"Proc. 15th Int. Conf. Inf. Fusion","author":"Huber","year":"2012"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9831196\/09835012.pdf?arnumber=9835012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:34:26Z","timestamp":1706769266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9835012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":36,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3193019","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}