A video compression-cum-classification network for classification from compressed video streams

Video analytics can achieve increased speed and efficiency by operating directly on the compressed video format, thereby alleviating the decoding burden on the analytics server. The encoded video streams are rich in semantic binary information and this information can be utilized more efficiently to train the classifiers. Motivated by the same notion, a deep learning-based video compression-cum-classification network has been proposed. In the proposed work, the binary-coded semantic information is extracted by using an auto encoder-based video compression component and the same fed to the MobileNetv2-based classifier for the classification of the given video streams based on their content. Using large-scale user-generated content provided by YouTube UGC dataset, it has been demonstrated that using deep neural networks for compression not only provides on-par compression results to traditional methods, it makes analytical processing of these videos faster. Video content tagging of YouTube UGC dataset has been used as the analytics task. The proposed DLVCC approach performs 10 x faster with 30 x fewer parameters than MobileNetv2 in video tagging of compressed video with no loss in accuracy.