Examining the applicability of virtual reality technique for video retrieval

Abstract

Query-By-Example (QBE) approach retrieves shots which are visually similar to example shots provided by a user. However, QBE cannot work if example shots are unavailable. To overcome this, this paper develops Query-By-Virtual-Example (QBVE) approach where example shots (virtual examples) for a query are created using virtual reality technique. A virtual example is created by synthesizing the user's gesture, 3D object and background image. Using large-scale video data, we examine the effectiveness of virtual examples from the perspective of video retrieval. In particular, we study about the comparison between virtual examples and example shots selected from real videos, the importance of camera movements, the combination strategy of gestures, 3D objects and backgrounds, and the individual difference in users.