Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Tso-Hsin Yeh"'
Autor:
Yu-Hung Liu, Tso-Hsin Yeh, Jui-Ting Shen, Zi-Jun Li, Chuan Kuo, Li-Chen Fu, Yu-Huan Yang, An-Sheng Liu
Publikováno v:
IROS
Since deep-learning-based method has been widely-used and is capable of generating generic model, most existing methods about action recognition use either two-stream structure, considering spatial and temporal features separately, or C3D, costing lo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::611463674167baf4d90762e75b36ec2b
https://doi.org/10.1109/iros40897.2019.8968533
https://doi.org/10.1109/iros40897.2019.8968533
Publikováno v:
Computer Vision – ACCV 2018 ISBN: 9783030208899
ACCV (2)
ACCV (2)
Recognizing human activities from unknown views is a challenging problem since human shapes appear quite differently from different viewpoints. In this paper, we learn a View-Invariant Pose (VIP) feature for depth-based cross-view action recognition.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a7e2dab682b45b5f20a15b256920ca1
https://doi.org/10.1007/978-3-030-20890-5_28
https://doi.org/10.1007/978-3-030-20890-5_28
Publikováno v:
SMC
Facial expression recognition(FER) is a challenging task even for human since individuals have their own way to express their feelings with different intensity. In order to extract commonality of facial expressions from different individuals, persona
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c3c7254806bb3032568a31e62e01f86
https://doi.org/10.1109/smc.2018.00405
https://doi.org/10.1109/smc.2018.00405
Publikováno v:
IROS
This paper proposes a new method for human posture recognition from top-view depth maps on small training datasets. There are two strategies developed to leverage the capability of convolution neural network (CNN) in mining the fundamental and generi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9342a47e85bb13889aa03d646139128d
https://doi.org/10.1109/iros.2017.8206273
https://doi.org/10.1109/iros.2017.8206273
Publikováno v:
SMC
In this paper, we propose an indoor action detection system which can automatically keep the log of users' activities of daily life since each activity generally consists of a number of actions. The hardware setting here adopts top-view depth cameras
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4344cd7eb66b299d7940632f02972d9e
https://doi.org/10.1109/smc.2016.7844868
https://doi.org/10.1109/smc.2016.7844868