Searching in Video Collections Using Sketches and Sample Images – The Cineast System
With the increasing omnipresence of video recording devices and the resulting abundance of digital video, finding a particular video sequence in ever-growing collections is more and more becoming a major challenge. Existing approaches to retrieve videos based on their content usually require prior knowledge about the origin and context of a particular video to work properly. Therefore, most state of the art video platforms still rely on text-based retrieval techniques to find desired sequences. In this paper, we present Cineast, a content-based video retrieval engine which retrieves video sequences based on their visual content. It supports Query-by-Example as well as Query-by-Sketch by using a multitude of low-level visual features in parallel. Cineast uses a collection of 200 videos from various genres with a combined length of nearly 20 h.
This work was partly supported by the Swiss National Science Foundation in the context of the CHIST-ERA project IMOTION (20CH21_151571).
- 1.Giangreco, I., Al Kabary, I., Schuldt, H.: ADAM – a database and information retrieval system for big multimedia collections. In: Proceedings of the IEEE International Congress on Big Data (BigData 2014). IEEE, Anchorage (2014)Google Scholar
- 2.Rossetto, L., Giangreco, I., Schuldt, H.: Cineast: a multi-feature sketch-based video retrieval engine. In: 2014 IEEE International Symposium on Multimedia (ISM), pp. 18–23. IEEE (2014)Google Scholar
- 3.Rossetto, L., Giangreco, I., Schuldt, H.: OSVC - Open Short Video Collection 1.0. Technical report CS-2015-002, University of Basel (2015)Google Scholar