Font Size:
ViTAG: A Learning Framework for Generating Action Tags in Videos
Last modified: 2013-07-09
Abstract
The volume of video media on the internet and from other sources is increasing at a rapid rate. The existing analysis, storage, retrieval, indexing and searching techniques are unable to cope with this huge volume of information. Moreover, there is no efficient way of extracting information from this huge pool. In this lieu, we propose a framework called 'Generating Action Tags and Videos' (ViTAG) for generating descriptions of videos. Our proposed framework for ViTAG is independent of domain specific techniques and can thus be applied for generating video descriptions in other domains. Video description can help in extracting useful information and patterns from the large volume of videos on the internet and improve existing indexing, searching and retrieval techniques. This paper describes the framework and the preliminary developments in implementation of the complete system.