A Bag-of-Words Equivalent Recurrent Neural Network for Action Recognition.
Computer Vision and Image Understanding(2017)
摘要
Traditional bag-of-words model can be formulated as an equivalent neural network.Joint supervised learning of classifier and visual vocabulary boosts performance.Kernel functions can be represented by non-linear neural network layers.Performance is maintained even when 90 percent of the input features are discarded. The traditional bag-of-words approach has found a wide range of applications in computer vision. The standard pipeline consists of a generation of a visual vocabulary, a quantization of the features into histograms of visual words, and a classification step for which usually a support vector machine in combination with a non-linear kernel is used. Given large amounts of data, however, the model suffers from a lack of discriminative power. This applies particularly for action recognition, where the vast amount of video features needs to be subsampled for unsupervised visual vocabulary generation. Moreover, the kernel computation can be very expensive on large datasets. In this work, we propose a recurrent neural network that is equivalent to the traditional bag-of-words approach but enables for the application of discriminative training. The model further allows to incorporate the kernel computation into the neural network directly, solving the complexity issue and allowing to represent the complete classification system within a single network. We evaluate our method on four recent action recognition benchmarks and show that the conventional model as well as sparse coding methods are outperformed.
更多查看译文
关键词
Action recognition,Bag-of-words,Neural networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络