IMOTION - A Content-Based Video Retrieval Engine

Abstract. This paper introduces the IMOTION system, a contentbased video retrieval engine, which is our proposed contribution for the 2015 Video Search Showcase. IMOTION is based on the Cineast system and was originally designed as a sketch-based video retrieval engine supporting multiple query paradigms. For the Video Search Showcase, it has been extended by dedicated motion features to allow for the specification of motion within a video sequence. For vector space retrieval, the IMOTION system exploits a large variety of low-level image and video features, as well as high-level spatial and temporal features that can all be jointly used in any combination. Thus, the IMOTION system supports query-by-sketch interactions (users provide sketches of video frames), motion queries (users specify motion across frames via partial flow fields), query-by-example (based on images) and any combination of these, and provides support for relevance feedback.

• Type: Journal
• Year: 2015
• Where: MMM
• Authors: Luca Rossetto, Ivan Giangreco, Heiko Schuldt, Stéphane Dupont, Omar Seddati, T. Metin Sezgin, Yusuf Sahillioglu
• Keywords: MMM 2015, Multimedia