Adding descriptive metadata, or labels, to a video is known as video annotation. It is comparable to picture annotation; the only difference is that it adds metadata descriptions to videos. Such a strategy is highly advantageous for video processing and can offer contextual knowledge of the video's content. It is possible to identify and classify individuals, groups, movements, or events in a film through annotation. Video Annotation Service, a subfield of computer vision, can benefit from machine learning techniques by making better annotations.