Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Konstantinos Bousmalis"'
Publikováno v:
Robotics: Science and Systems
Imitation learning is an effective tool for robotic learning tasks where specifying a reinforcement learning (RL) reward is not feasible or where the exploration problem is particularly difficult. Imitation, typically behavior cloning or inverse RL,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::adca0fb288bff4c4349ba0f3099100b4
Autor:
Stephan Gouws, Forrester Cole, Kevin Murphy, Fred Bertsch, Amelie Royer, Inbar Mosseri, Konstantinos Bousmalis
Publikováno v:
Domain Adaptation for Visual Understanding ISBN: 9783030306700
Domain Adaptation for Visual Understanding
Domain Adaptation for Visual Understanding
Image translation refers to the task of mapping images from a visual domain to another. Given two unpaired collections of images, we aim to learn a mapping between the corpus-level style of each collection, while preserving semantic content shared ac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca3ad0f78c2ca63af4aa0bd05c414f29
https://doi.org/10.1007/978-3-030-30671-7_3
https://doi.org/10.1007/978-3-030-30671-7_3
Autor:
Thomas Lampe, Yusuf Aytar, Jackie Kay, Konstantinos Bousmalis, Yuxiang Zhou, Rae Jeong, David Khosid, Francesco Nori
Publikováno v:
ICRA
Collecting and automatically obtaining reward signals from real robotic visual data for the purposes of training reinforcement learning algorithms can be quite challenging and time-consuming. Methods for utilizing unlabeled data can have a huge poten
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f11610deddc8cdc230ba99eac4b212c
http://arxiv.org/abs/1910.09470
http://arxiv.org/abs/1910.09470
Autor:
Behnam Gholami, Vladimir Pavlovic, Konstantinos Bousmalis, Pritish Kumar Sahu, Ognjen Rudovic
Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where there is a single, labeled, source and a single target domain. However, in many real-world settings one seeks to adapt to multiple, but somewhat similar, target d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b8e9f81497dd477a67fe45f46f4bc8f
http://arxiv.org/abs/1810.11547
http://arxiv.org/abs/1810.11547
Autor:
Alex Irpan, Sergey Levine, Vincent Vanhoucke, Konstantinos Bousmalis, Paul Wohlhart, Peter Pastor, Laura Downs, Julian Ibarz, Yunfei Bai, Matthew Kelcey, Mrinal Kalakrishnan, Kurt Konolige
Publikováno v:
ICRA
Instrumenting and collecting annotated visual grasping datasets to train modern machine learning algorithms can be extremely time-consuming and expensive. An appealing alternative is to use off-the-shelf simulators to render synthetic data for which
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c7f9eb38a322db476b954fd724bbbc1
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 24:170-177
Hidden conditional random fields (HCRFs) are discriminative latent variable models that have been shown to successfully learn the hidden structure of a given classification problem (provided an appropriate validation of the number of hidden states).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8fead19206a14d107331b875dbf8aed3
https://doi.org/10.1109/tnnls.2012.2224882
https://doi.org/10.1109/tnnls.2012.2224882
Publikováno v:
CVPR
Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated automatically. Unfortun
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::20439e49d96697d08941debaf62a917a
Autor:
Konstantinos Bousmalis, Stefanos Zafeiriou, Louis-Philippe Morency, Maja Pantic, Zoubin Ghahramani
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence, 37(9), 1917-1929. IEEE Computer Society
Hidden conditional random fields (HCRFs) are discriminative latent variable models which have been shown to successfully learn the hidden structure of a given classification problem. An Infinite hidden conditional random field is a hidden conditional
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f809710f1df7f4383ab49b771a14a5e2
https://pubmed.ncbi.nlm.nih.gov/26353136
https://pubmed.ncbi.nlm.nih.gov/26353136
Semi-Non-negative Matrix Factorization is a technique that learns a low-dimensional representation of a dataset that lends itself to a clustering interpretation. It is possible that the mapping between this new representation and our original data ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf8c5fab54bb309c36d84db39c7aa897
Publikováno v:
Image and Vision Computing
Image and vision computing, 31(2), 203-221. Elsevier
Image and vision computing, 31(2), 203-221. Elsevier
While detecting and interpreting temporal patterns of nonverbal behavioural cues in a given context is a natural and often unconscious process for humans, it remains a rather difficult task for computer systems. Nevertheless, it is an important one t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c1105e1aee9b513283b147d4680bf520