Learn More
Recently, deep learning approach, especially deep Convolutional Neural Networks (ConvNets), have achieved overwhelming accuracy with fast processing speed for image classification. Incorporating temporal structure with deep ConvNets for video representation becomes a fundamental problem for video content analysis. In this paper, we propose a new approach,(More)
Recently, newly invented features (e.g. Fisher vector, VLAD) have achieved state-of-the-art performance in large-scale video analysis systems that aims to understand the contents in videos, such as concept recognition and event detection. However, these features are in high-dimensional representations, which remarkably increases computation costs and(More)
To choose proper parameters for our method, we perform experiments with different parameter settings. We first study how to choose the number of hidden units and report the results in Table 1. For simplification, we set the number of hidden units in LSTMs from the encoder and the decoder as the same. The result shows that the performance of our method can(More)
In this work, we consider the problem of robust principal component analysis (RPCA) for streaming noisy data that has been highly compressed. This problem is prominent when one deals with high-dimensional and large-scale data and data compression is necessary. To solve this problem, we propose an online compressed RPCA algorithm to efficiently recover the(More)
  • 1