Histogram of phrase correlation combined with MIL for human action recognition

Abstract

In this paper, we propose a new feature called HPC (Histogram of Phrase Correlation) for human action based on phrase correlation. For classification, use a multiple instance learning framework to describe the HPC features as instances. By using a discriminative approach, we embed each video into HPC-based space and the coordinates of the video in that space are used for classification by using the k-nearest neighbor algorithm. Experiments show that the HPC feature is a useful feature for describing actions.