Multimedia Information Retrieval: Video Browsing

With advent of internet, there has been tremendous surge in search for videos. Research suggests that users spend a lot of time browsing: viewing part of one video after another while watching only a few of the videos to its completion. This is termed as seek, a special form of browsing repeating partial viewing of the same video. This impacts the network bandwidth resulting in streaming issues with the browser. We propose to devise a system where the user would be able to view pre selected video sequence which would contain parts required by the user. This method of video browsing would be significant improvement over the traditional video browsing in terms of efficiency and user friendliness. Keywords—video processing, frames, visual recognition, image indexing, visual content tags