{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T22:56:05Z","timestamp":1752360965698,"version":"3.28.0"},"reference-count":60,"publisher":"SPIE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4,13]]},"DOI":"10.1117\/12.2309945","type":"proceedings-article","created":{"date-parts":[[2018,4,16]],"date-time":"2018-04-16T16:50:54Z","timestamp":1523897454000},"page":"58","source":"Crossref","is-referenced-by-count":15,"title":["Reinforcement learning in computer vision"],"prefix":"10.1117","author":[{"given":"Alexander V.","family":"Bernstein","sequence":"first","affiliation":[]},{"given":"E. V.","family":"Burnaev","sequence":"first","affiliation":[]}],"member":"189","reference":[{"key":"c1","first-page":"292","article-title":"Learning-Based Robot Vision","volume":"2048","author":"Pauli","year":"2001"},{"key":"c2","doi-asserted-by":"publisher","DOI":"10.1109\/34.982903"},{"key":"c3","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-008-9235-4"},{"key":"c4","first-page":"1239","article-title":"Learning nonlinear appearance manifolds for robot localization","author":"Ham","year":"2005"},{"key":"c5","doi-asserted-by":"publisher","DOI":"10.1016\/S0262-8856(00)00108-6"},{"key":"c6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-62416-7"},{"article-title":"Machine Learning in Appearance-based Robot Selflocalization","year":"2017","author":"Kuleshov","key":"c7"},{"key":"c8","first-page":"237","article-title":"Reinforcement learning: A survey","volume":"4","author":"Kaelbling","year":"1996"},{"key":"c9","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015008417172"},{"article-title":"Reinforcement learning: an introduction (Adaptive computation and machine learning)","year":"1998","author":"Sutton","key":"c10"},{"key":"c11","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1080.0305"},{"key":"c12","first-page":"116","article-title":"Adaptive design of experiments based on gaussian processes","volume":"9047","author":"Burnaev","year":"2015"},{"key":"c13","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-017-9542-1"},{"article-title":"Markovian Decision Processes - Discrete Stochastic Dynamic Programming","year":"1994","author":"Puterman","key":"c14"},{"article-title":"Dynamic Programming","year":"1957","author":"Bellman","key":"c15"},{"article-title":"Dynamic Programming: Deterministic and Stochastic Models","year":"1987","author":"Bertsekas","key":"c16"},{"article-title":"Learning from Delayed Reward","year":"1989","author":"Watkins","key":"c17"},{"key":"c18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"c19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"c20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"c21","first-page":"881","article-title":"PAC Model-Free Reinforcement Learning","author":"Strehl","year":"2006"},{"key":"c22","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"c23","first-page":"1","article-title":"A Brief Survey of Deep Reinforcement Learning","author":"Arulkumaran","year":"2017"},{"key":"c24","first-page":"1","article-title":"Deep Reinforcement Learning: An Overview","author":"Li","year":"2017"},{"key":"c25","first-page":"1","article-title":"A Reinforcement Learning Framework for Parameter Control in Computer Vision Applications","author":"Taylor","year":"2004"},{"key":"c26","doi-asserted-by":"publisher","DOI":"10.1109\/34.659932"},{"key":"c27","first-page":"246","article-title":"Application of opposition-based reinforcement learning in image segmentation","author":"Sahba","year":"2007"},{"key":"c28","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2006.12.003"},{"issue":"8","key":"c29","first-page":"1","article-title":"Application of reinforcement learning for segmentation of transrectal ultrasound images","volume":"8","author":"Sahba","year":"2008"},{"key":"c30","doi-asserted-by":"publisher","DOI":"10.5899\/2017\/cacsa-00072"},{"key":"c31","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2008.4631278"},{"key":"c32","first-page":"60","article-title":"A Q-Learning Approach to Decision Problems in Image Processing","author":"Gherega","year":"2012"},{"key":"c33","first-page":"285","article-title":"Interactive Selection of Visual Features through Reinforcement Learning","author":"Jodogne","year":"2004"},{"key":"c34","first-page":"469","article-title":"Multi-Table Reinforcement Learning for Visual Object Recognition","author":"Pinol","year":"2012"},{"key":"c35","first-page":"33","article-title":"Feature Selection Based on Reinforcement Learning for Object Recognition","author":"Pinol","year":"2012"},{"key":"c36","first-page":"1","article-title":"Reinforcement learning of visual descriptors for object recognition","author":"Pinol","year":"2014"},{"key":"c37","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-015-0893-y"},{"article-title":"Digital image processing","year":"1991","author":"Pratt","key":"c38"},{"key":"c39","doi-asserted-by":"publisher","DOI":"10.1117\/12.2268723"},{"article-title":"Visual Feature Learning","year":"2001","author":"Piater","key":"c40"},{"article-title":"Visual Feature Learning","year":"2015","author":"Zhu","key":"c41"},{"key":"c42","first-page":"102530G","article-title":"Manifold Learning in Machine Vision and Robotics","volume":"10253","author":"Bernstein","year":"2017"},{"key":"c43","doi-asserted-by":"publisher","DOI":"10.1142\/WSSRIS"},{"key":"c44","doi-asserted-by":"publisher","DOI":"10.1109\/70.538972"},{"key":"c45","doi-asserted-by":"publisher","DOI":"10.1109\/70.143350"},{"key":"c46","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.250573"},{"key":"c47","first-page":"33","article-title":"Reinforcement learning to adjust robot movements to new situations","volume":"6","author":"Kober","year":"2011"},{"key":"c48","first-page":"57","article-title":"Learning to control a low-cost manipulator using data-efficient reinforcement learning","volume":"7","author":"Deisenroth","year":"2012"},{"key":"c49","first-page":"1","article-title":"Autonomous reinforcement learning on raw visual input data in a real world application","author":"Lange","year":"2012"},{"key":"c50","first-page":"1","article-title":"Acquiring visual servoing reaching and grasping skills using neural reinforcement learning","author":"Lampe","year":"2013"},{"key":"c51","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-014-0151-5"},{"key":"c52","first-page":"1","article-title":"Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control","author":"Zhang","year":"2015"},{"issue":"39","key":"c53","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016"},{"key":"c54","first-page":"1","article-title":"Deep Spatial Autoencoders for Visuomotor Learning","author":"Finn","year":"2016"},{"key":"c55","first-page":"1","article-title":"Learning Visual Servoing with Deep Features and Fitted Q-iteration","author":"Lee","year":"2017"},{"key":"c56","first-page":"2303","article-title":"Environment Exploration for Object-Based Visual Saliency Learning","author":"Craye","year":"2016"},{"key":"c57","first-page":"1","article-title":"CAD2RL: Real Single-Image Flight Without a Single Real Image","author":"Sadegh","year":"2017"},{"key":"c58","first-page":"1","article-title":"Deep Reinforcement Learning for Visual Object Tracking in Videos","author":"Zhang","year":"2017"},{"key":"c59","first-page":"1","article-title":"Collaborative Deep Reinforcement Learning for Joint Object Search","author":"Kong","year":"2017"},{"key":"c60","first-page":"1","article-title":"Active Object Localization with Deep Reinforcement Learning","author":"Caicedo","year":"2015"}],"event":{"name":"Tenth International Conference on Machine Vision (ICMV 2017)","start":{"date-parts":[[2017,11,13]]},"location":"Vienna, Austria","end":{"date-parts":[[2017,11,15]]}},"container-title":["Tenth International Conference on Machine Vision (ICMV 2017)"],"original-title":[],"deposited":{"date-parts":[[2018,5,23]],"date-time":"2018-05-23T23:30:11Z","timestamp":1527118211000},"score":1,"resource":{"primary":{"URL":"https:\/\/spiedigitallibrary.org\/conference-proceedings-of-spie\/10696\/2309945\/Reinforcement-learning-in-computer-vision\/10.1117\/12.2309945.full"}},"subtitle":[],"editor":[{"given":"Jianhong","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Petia","family":"Radeva","sequence":"first","affiliation":[]},{"given":"Dmitry","family":"Nikolaev","sequence":"first","affiliation":[]},{"given":"Antanas","family":"Verikas","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2018,4,13]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1117\/12.2309945","relation":{},"subject":[],"published":{"date-parts":[[2018,4,13]]}}}