Object recognition in real-world environments is one of the fundamental and key tasks in
computer vision and robotics communities. With the advanced sensing technologies and low …

Many machine learning problems are concerned with discovering or associating common
patterns in data of multiple views or modalities. Multi-view learning is one of the methods to …

Recognizing objects and scenes are two challenging but essential tasks in image
understanding. In particular, the use of RGB-D sensors in handling these tasks has emerged …

In this paper, we introduce a novel methodology for fusing sensors and improving
robustness to sensor failures in end-to-end learning based autonomous navigation of …

First-person videos have unique characteristics such as heavy egocentric motion, strong
preceding events, salient transitional activities and post-event impacts. Action recognition …

Research interest in autonomous control of unmanned aerial vehicles (UAVs) has increased
rapidly over the past decade. They are now widely used in civilian, military, and private …

A key issue in RGBD classification is how to fuse the RGB and depth modalities. A popular
way is to extract the private features of unimodality and the common features between the …

This paper presents a novel optimization technique in image processing for emotion
recognition based on facial expression. The method combines two pre-processing filters …

物体识别是机器视觉研究的主要内容之一, 融合物体深度特征的RGB-D 图像为物体识别精度的
提高提供了新的解决途径. 为系统总结其近年产生的诸多成果, 首先综述了基于RGB-D …

Creating color difference and improving the color resolution in digital imaging is crucial for
better application of color analysis. Herein, a novel color modulation analysis strategy was …