Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Agethen, Sebastian"'
Autor:
Agethen, Sebastian, Hsu, Winston H.
Action recognition greatly benefits motion understanding in video analysis. Recurrent networks such as long short-term memory (LSTM) networks are a popular choice for motion-aware sequence learning tasks. Recently, a convolutional extension of LSTM w
Externí odkaz:
http://arxiv.org/abs/1908.08990
This paper proposes a robust localization system that employs deep learning for better scene representation, and enhances the accuracy of 6-DOF camera pose estimation. Inspired by the fact that global scene structure can be revealed by wide field-of-
Externí odkaz:
http://arxiv.org/abs/1904.09722
Autor:
Agethen, Sebastian, Hsu, Winston H.
We present a new supervised architecture termed Mediated Mixture-of-Experts (MMoE) that allows us to improve classification accuracy of Deep Convolutional Networks (DCN). Our architecture achieves this with the help of expert networks: A network is t
Externí odkaz:
http://arxiv.org/abs/1511.06072
The recent promising achievements of deep learning rely on the large amount of labeled data. Considering the abundance of data on the web, most of them do not have labels at all. Therefore, it is important to improve generalization performance using
Externí odkaz:
http://arxiv.org/abs/1511.06104
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Agethen, Sebastian, Hsu, Winston H.
Publikováno v:
2016 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 2016, p2687-2691, 5p
