ISSN : 2319-7323


Open Access


Title : Visual Attention Key Frame Extraction for Video Annotations.
Authors : Prof.Archana.V.Potnurwar, Dr Mohammad Atique
Keywords : Visual attention ,keyframe, time constraint clustering.
Issue Date : January 2014
Abstract : The insufficiency of labeled training data for representing the distribution of the entire dataset is a major obstacle in automatic semantic annotation of large-scale video database the objective is to represent the most “important” or “meaningful” scenes of the large amount of visual information by only a few images:the key frames. First, the image sequences are temporally segmented into continuous segments called shots.Then a few frames of each shot are selected as key frames.In this paper ,retrieving videos using key words requires obtaining the semantic features of the videos. Most work reported in the literature focuses on keyframe extraction methods in the video shot.The focus is on visual attention Keyframe extraction(VAKE).
Page(s) : 39-42
ISSN : 2319-7323
Source : Vol. 3, No.1