Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Myunggi Lee"'
Autor:
Mingon Kim, Joonbo Chae, Jiyong Oh, Myunggi Lee, Sangyup Yi, Yongjin Lee, Sanghyun Kim, Minsung Kim, Hosang Lee, Nojun Kwak, Seho Shin, Beomyeong Park, Soonwook Hwang, Hyunbum Cho, Kyong-Sok K.C. Chang, Sangkuk Lee, Sumin Park, Yisoo Lee, Wonje Choi, Jimin Lee, Jaeheung Park, Jaehoon Sim, Jaesug Jung
Publikováno v:
Journal of Field Robotics. 34:359-380
This paper presents the technical approaches used and experimental results obtained by Team SNU Seoul National University at the 2015 DARPA Robotics Challenge DRC Finals. Team SNU is one of the newly qualified teams, unlike 12 teams who previously pa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::122e56fdabdf0bfbeaf51fe92566c136
https://doi.org/10.1002/rob.21678
https://doi.org/10.1002/rob.21678
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012489
ECCV (10)
ECCV (10)
Spatio-temporal representations in frame sequences play an important role in the task of action recognition. Previously, a method of using optical flow as a temporal information in combination with a set of RGB images that contain spatial information
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b1a4a7bc1a7089091192b382254bead7
https://doi.org/10.1007/978-3-030-01249-6_24
https://doi.org/10.1007/978-3-030-01249-6_24
Publikováno v:
IJCNN
Most of recent successful researches on action recognition are based on deep learning structures. Nonetheless, training deep neural networks is notorious for requiring huge amount of data. On the other hand, not enough data can lead to an overfitted
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2fb376589faef15fabd85560d8fb608c
https://doi.org/10.1109/ijcnn.2017.7965886
https://doi.org/10.1109/ijcnn.2017.7965886
Publikováno v:
Neural Information Processing ISBN: 9783319466804
ICONIP (4)
ICONIP (4)
Deep learning has been a growing trend in various fields of natural image classification as it performs state-of-the-art result on several challenging tasks. Despite its success, deep learning applied to medical image analysis has not been wholly exp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::41453e4875c7e34c484780c650ba94c7
https://doi.org/10.1007/978-3-319-46681-1_3
https://doi.org/10.1007/978-3-319-46681-1_3
Autor:
Joonbo Chae, Kyong-Sok K.C. Chang, Beomyeong Park, Sangkuk Lee, Minsung Kim, Soonwook Hwang, Hyunbum Cho, Jimin Lee, Hosang Lee, Myunggi Lee, Sangyup Yi, Jaesug Jung, Jaeheung Park, Nojun Kwak, Yongjin Lee, Jaehoon Sim, Seho Shin, Mingon Kim, Sanghyun Kim
Publikováno v:
Humanoids
This paper presents the technical approaches including the system architecture and the controllers that have been used by Team SNU at the DARPA Robotics Challenge (DRC) Finals 2015. The platform THORMANG we used is a modular humanoid robot developed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c784bd9a209bdef0112515bc443cab05
https://doi.org/10.1109/humanoids.2015.7363458
https://doi.org/10.1109/humanoids.2015.7363458