• Publications
  • Influence
Vehicle Type Classification Using Unsupervised Convolutional Neural Network
We propose an appearance-based vehicle type classification method from vehicle frontal view images by using an unsupervised convolutional neural network. Expand
  • 70
  • 6
  • PDF
Identification of the role of a MAP kinase Tmk2 in Hypocrea jecorina (Trichoderma reesei)
Despite the important role of MAPKs in signal transduction, their functions in the cellulase hyper-producing filamentous fungus Hypocrea jecorina haven't been studied except for the Hog1-like Tmk3.Expand
  • 35
  • 1
Regulation of cellulase expression, sporulation, and morphogenesis by velvet family proteins in Trichoderma reesei
Homologs of the velvet protein family are encoded by the ve1, vel2, and vel3 genes in Trichoderma reesei. To test their regulatory functions, the velvet protein-coding genes were disrupted,Expand
  • 19
Visual tracking with sparse correlation filters
We propose a sparse correlation filter for visual object tracking, which combines the effectiveness of sparse representation and the computational efficiency of correlation filters. Expand
  • 6
  • PDF
The identification of and relief from Fe3+ inhibition for both cellulose and cellulase in cellulose saccharification catalyzed by cellulases from Penicillium decumbens.
Lignocellulosic biomass is an underutilized, renewable resource that can be converted to biofuels. The key step in this conversion is cellulose saccharification catalyzed by cellulase. In this work,Expand
  • 12
Vehicle Color Recognition Based on License Plate Color
We present a new method for vehicle color recognition, which is based on license plate color. Expand
  • 5
Stitching Videos from a Fisheye Lens Camera and a Wide-Angle Lens Camera for Telepresence Robots
We present a multi-homography-based video stitching method which stitches videos from a wide-angle camera and a fisheye lens for telepresence robots. Expand
  • 2
  • PDF
Online Multi-Person Tracking Based on Metric Learning
The correct associations of detections and tracklets are the key to online multi-person tracking. Expand
Multi-layer CNN Features Aggregation for Real-time Visual Tracking
In this paper, we propose a novel convolutional neural network based tracking framework, which aggregates multiple CNN features from different layers into a robust representation and realizes real-time tracking. Expand
Can You Easily Perceive the Local Environment? A User Interface with One Stitched Live Video for Mobile Robotic Telepresence Systems
In this paper, we propose to use a user interface with one stitched live video instead of two live videos for mobile robotic telepresence systems. Expand