Title :
On-the-fly specific person retrieval
Author :
Parkhi, Omkar M. ; Vedaldi, Andrea ; Zisserman, Andrew
Author_Institution :
Dept. of Eng. Sci., Univ. of Oxford, Oxford, UK
Abstract :
We describe a method of visual search for finding people in large video datasets. The novelty is that the person of interest can be specified at run time by a text query, and a discriminative classifier for that person is then learnt on-the-fly using images downloaded from Google Image search. The performance of the method is evaluated on a ground truth dataset of episodes of Scrubs, and results are also shown for retrieval on the TRECVid 2011 IACC.1.B dataset of over 8k videos. The entire process from specifying the query to receiving the ranked results takes only a matter of seconds.
Keywords :
image classification; image retrieval; search engines; text analysis; video signal processing; Google image search; Scrubs; TRECVid 2011 IACC.1.B dataset; discriminative classifier; large video datasets; on-the-fly specific person retrieval; text query; visual search method; Detectors; Face; Facial features; Feature extraction; Google; Training; Vectors;
Conference_Titel :
Image Analysis for Multimedia Interactive Services (WIAMIS), 2012 13th International Workshop on
Conference_Location :
Dublin
Print_ISBN :
978-1-4673-0791-8
Electronic_ISBN :
2158-5873
DOI :
10.1109/WIAMIS.2012.6226775
