Presentation 2012-03-30
Evaluating the Effectiveness of Virtual Reality Technique for Query-by-Example Video Retrieval
Kimiaki SHIRAHAMA, Tomomi KOUMURA, Kuniaki UEHARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Query-By-Example (QBE) retrieves shots which contain similar features (e.g., color, edge and motion) to those of example shots provided as a query. One crucial problem of OBE is the diversity of shots, where even for the same query, relevant shots contain significantly diffrent features due to varied camera techniques. QBE approach is impractical if it requires the user to provide a large number of example shots in order to retrieve diverse relevant shots. Thus, we are developing Query-By-Virtual-Example (QBVE) approach which can efficiently create a large number of virtual example shots by synthesizing the user's gesture, 3D object and background image. In this paper, using large-scale video data, we examine the effectiveness of virtual example shots from the perspective of retrieval performance. In addition, we study about the importance of camera movements, the individual difference in users, and the synthesis strategy of gestures, 3D objects and backgrounds.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Query by virtual example / Virtual reality / Virtual example / Image and motion features
Paper # PRMU2011-269,HIP2011-97
Date of Issue

Conference Information
Committee HIP
Conference Date 2012/3/22(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Evaluating the Effectiveness of Virtual Reality Technique for Query-by-Example Video Retrieval
Sub Title (in English)
Keyword(1) Query by virtual example
Keyword(2) Virtual reality
Keyword(3) Virtual example
Keyword(4) Image and motion features
1st Author's Name Kimiaki SHIRAHAMA
1st Author's Affiliation Graduate School of Economics, Kobe University()
2nd Author's Name Tomomi KOUMURA
2nd Author's Affiliation Graduate School of System Informatics, Kobe University
3rd Author's Name Kuniaki UEHARA
3rd Author's Affiliation Graduate School of System Informatics, Kobe University
Date 2012-03-30
Paper # PRMU2011-269,HIP2011-97
Volume (vol) vol.111
Number (no) 500
Page pp.pp.-
#Pages 6
Date of Issue