We propose a novel method that exploits visual information of ideograms and logograms in analyzing Japanese review documents. Our method first converts font images of Japanese characters into character embeddings using convolutional neural networks. It then constructs document embeddings from the character embeddings based on Hierarchical Attention Networks, which represent the documents based ...

This study describes the design of the NTNU-YZU system for the automated evaluation of scientific writing shared task. We employ a convolutional neural network with the Word2Vec/GloVe embedding representation to predict whether a sentence needs language editing. For the Boolean prediction track, our best F-score of 0.6108 ranked second among the ten submissions. Our system also achieved an F-sc...

We introduce tensor field networks, which are locally equivariant to 3D rotations and translations (and invariant to permutations of points) at every layer. 3D rotation equivariance removes the need for data augmentation to identify features in arbitrary orientations. Our network uses filters built from spherical harmonics; due to the mathematical consequences of this filter choice, each layer ...

One of the most important parts of environment perception is the detection of obstacles in the surrounding of the vehicle. To achieve that, several sensors like radars, LiDARs and cameras are installed in autonomous vehicles. The produced sensor data is fused to a general representation of the surrounding. In this thesis the dynamic occupancy grid map approach of Nuss et al. [37] is used while ...

This seminar paper focusses on convolutional neural networks and a visualization technique allowing further insights into their internal operation. After giving a brief introduction to neural networks and the multilayer perceptron, we review both supervised and unsupervised training of neural networks in detail. In addition, we discuss several approaches to regularization. The second section in...

09.15 10.45 Paper Session I o Exploiting the PANORAMA Representation for Convolutional Neural Network Classification and Retrieval Konstantinos Sfikas, Theoharis Theoharis and Ioannis Pratikakis o LightNet: A Lightweight 3D Convolutional Neural Network for Real-Time 3D Object Recognition Shuaifeng Zhi, Yongxiang Liu, Xiang Li and Yulan Guo o Unstructured point cloud semantic labeling using deep...

Understanding human actions in wild videos is an important task with a broad range of applications. In this paper we propose a novel approach named Hierarchical Attention Network (HAN), which enables to incorporate static spatial information, short-term motion information and long-term video temporal structures for complex human action understanding. Compared to recent convolutional neural netw...

Lung nodule classification is a class imbalanced problem because nodules are found with much lower frequency than non-nodules. In the class imbalanced problem, conventional classifiers tend to be overwhelmed by the majority class and ignore the minority class. We therefore propose cascaded convolutional neural networks to cope with the class imbalanced problem. In the proposed approach, multi-s...

Model based iterative reconstruction (MBIR) algorithms for low-dose X-ray CT are computationally expensive. To address this problem, we recently proposed the world-first deep convolutional neural network (CNN) for low-dose X-ray CT and won the second place in 2016 AAPM Low-Dose CT Grand Challenge. However, some of the texture were not fully recovered. To cope with this problem, here we propose ...