3 papers
cs.CV2019
Deep Multi-Kernel Convolutional LSTM Networks and an Attention-Based Mechanism for Videos
Sebastian Agethen, Winston H. Hsu
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…
cs.CV2019
FishNet: A Camera Localizer using Deep Recurrent Networks
Hsin-I Chen, Sebastian Agethen, Chiamin Wu +2
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…
cs.NE2015
Semi-supervised Learning for Convolutional Neural Networks via Online Graph Construction
Sheng-Yi Bai, Sebastian Agethen, Ting-Hsuan Chao +1
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. T…