Convolutional network techniques have recently achieved great success in vision based detection tasks. This paper introduces the recent development of our research on transplanting the fully convolutional network technique to the detection tasks on 3D range scan data. Specifically, the scenario is set as the vehicle detection task from the range data of Velodyne 64E lidar. We proposes to presen...

Recent years have witnessed the great progress for semantic segmentation using deep convolutional neural networks (DCNNs). This paper presents a novel fully convolutional network for semantic segmentation using multi-scale contextual convolutional features. Since objects in natural images tend to be with various scales and aspect ratios, capturing the rich contextual information is very critica...

Multiword expressions (MWEs) are lexical items that can be decomposed into multiple component words, but have properties that are unpredictable with respect to their component words. In this paper we propose the first deep learning models for token-level identification of MWEs. Specifically, we consider a layered feedforward network, a recurrent neural network, and convolutional neural networks...

Recently, deep learning methods have made a significant improvement in compressive sensing image reconstruction task. However, it still remains a problem of block effect which degrades the reconstruction results. In this paper, we propose a fully-convolutional network, where the full image is directly measured with a convolutional layer. Thanks to the overlapped convolutional measurement, the b...

In this paper, we propose the Broadcasting Convolutional Network (BCN) that extracts key object features from the global field of an entire input image and recognizes their relationship with local features. BCN is a simple network module that collects effective spatial features, embeds location information and broadcasts them to the entire feature maps. We further introduce the Multi-Relational...

We propose a retrieval-augmented convolutional network and propose to train it with local mixup, a novel variant of the recently proposed mixup algorithm. The proposed hybrid architecture combining a convolutional network and an off-theshelf retrieval engine was designed to mitigate the adverse effect of off-manifold adversarial examples, while the proposed local mixup addresses on-manifold one...

This paper proposes a viewpoint invariant face recognition method in which several viewpoint dependent classifiers are combined by a gating network. The gating network is designed as autoencoder with competitive hidden units. The viewpoint dependent representations of faces can be obtained by this autoencoder from many faces with different views. Multinomial logit model is used for the viewpoin...

In this paper, we study joint network/channel decoding for multi–source multi–relay heterogeneous wireless networks. When convolutional and network codes are used at the physical and network layers, respectively, we show that error correction and diversity properties of the whole network can be characterized by an equivalent and distributed convolutional network/channel code. In particular, it ...