Motion-sketch based Video Retrieval using a Trellis Levenshtein Distance
Tools
Tools
Tools
Hu, R and Collomosse, J (2010) Motion-sketch based Video Retrieval using a Trellis Levenshtein Distance In: Intl. Conference on Pattern Recognition (ICPR) 2010, 2010 - ?, Istanbul, Turkey.
![[img]](/style/images/fileicons/application_pdf.png)
| PDF - Accepted Version 1755Kb |
Abstract
We present a fast technique for retrieving video clips using free-hand sketched queries. Visual keypoints within each video are detected and tracked to form short trajectories, which are clustered to form a set of spacetime tokens summarising video content. A Viterbi process matches a space-time graph of tokens to a description of colour and motion extracted from the query sketch. Inaccuracies in the sketched query are ameliorated by computing path cost using a Levenshtein (edit) distance. We evaluate over datasets of sports footage.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Divisions: | Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing |
| ID Code: | 605296 |
| Deposited By: | Symplectic Elements |
| Deposited On: | 31 May 2012 10:41 |
| Last Modified: | 01 Apr 2013 14:40 |
Document Downloads
Repository Staff Only: item control page