Paper Title
Video Summarization: Study of Various Techniques

Abstract
A comparative study of various techniques which can be used for summarization of Videos i.e. Video to Video conversion is presented along with respective architec- ture, results, strengths and shortcomings. In all approaches, a lengthy video is converted into a shorter video which aims to capture all important events that are present in the original video. The definition of ’im- portant event’ may vary according to the context, such as a sports video and a documentary may have different events which are classified as important. Keywords - Video Summarization, DNN, RNN, Deep Semantic Features, Confusion Matrix