Digital videos have become the medium of choice for a growing number of people communicating via Internet and their mobile devices. Over the past decade, world has witnessed an explosive growth in the amount of video data fostered by astonishing technological developments. In this scenario, there is a growing demand for efficient systems to reduce the work and information overload for people. Making efficient use of video content requires the development of intelligent tools capable to understand videos in a similar way as humans do. This has been the goal of a quickly evolving research area known as video understanding. One of the main issues concerning the video understanding problem is the extraction of useful information from video content. Recently, deep learning has been successfully used to learn powerful and interpretable features for understanding visual content. However, deep learning faces some challenges for dealing with the temporal dimension of video data, like limited training samples and high computational cost. Since video data are usually available in compressed form, it is desirable to directly process the compressed video without decoding. This enables us to save high computational load and memory usage in full decoding the video stream. This Scientific Initiation project aims to investigate different compressed domain video features based on deep neural networks.
News published in Agência FAPESP Newsletter about the scholarship: