• Ensemble video object cut in highly dynamic scenes 

    Ren, Xiaobo (University of Missouri--Columbia, 2014)
    [ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] We consider video object cut as an ensemble of framelevel background-foreground object classifiers which fuses information across frames and refine ...
  • Fast and reliable hand action recognition 

    Ou, Jingxin (University of Missouri--Columbia, 2014)
    [ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] In this work, we develop a hand action recognition method using a SVM (Support Vector Machine) classifier with HOG (Histogram of Oriented Gradients) ...
  • Learning human poses in natural scenes 

    Ning, Guanghan (University of Missouri--Columbia, 2018)
    [ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] The task of human pose estimation in natural scenes is to determine the precise pixel locations of body keypoints. It is very important for many ...
  • Moving objects detection and labeling in surveillance videos 

    Zhu, Yizhe (University of Missouri--Columbia, 2014)
    Moving objects detection and labeling are an important component of intelligent surveillance systems. Accurate classification of moving objects allows the monitoring system to react to certain events of interest. In this ...
  • Performance analysis of mix-kernel convolutional neural network 

    Huang, Yibin (University of Missouri--Columbia, 2016)
    Deep convolutional neural networks (DCNN) have achieved the state-of-the-art performance in a number of computer vision tasks in recent years, including object detection, classification and recognition. The DCNN is very ...
  • Person re-identification with pairwise learning and ranking 

    Zhang, Zhi (University of Missouri--Columbia, 2014)
  • Robust person tracking in indoor environments 

    Zeng, Yifeng (University of Missouri--Columbia, 2014)
    [ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.]
  • Stock market forecasting using recurrent neural network 

    Gao, Qiyuan (University of Missouri--Columbia, 2016)
    In this research, we study the problem of stock market forecasting using Recurrent Neural Network(RNN) with Long Short-Term Memory (LSTM). The purpose of this research is to examine the feasibility and performance of LSTM ...
  • Towards real-time object detection on edge with deep neural networks 

    Zhang, Zhi (University of Missouri--Columbia, 2018)
    Despite being a core topic for more than several decades, object detection is still receiving increasing attentions due to its irreplaceable importance in a wide variety of applications. Abundant object detectors based on ...