DMCA
Annotated Free-Hand Sketches for Video Retrieval Using Object Semantics and Motion (2012)
| Citations: | 2 - 1 self |
BibTeX
@MISC{Hu12annotatedfree-hand,
author = {Rui Hu and Stuart James and John Collomosse},
title = {Annotated Free-Hand Sketches for Video Retrieval Using Object Semantics and Motion},
year = {2012}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. We present a novel video retrieval system that accepts annotated free-hand sketches as queries. Existing sketch based video retrieval (SBVR) systems enable the appearance and movements of objects to be searched naturally through pictorial representations. Whilst visually expressive, such systems present an im-precise vehicle for conveying the semantics (e.g. object types) within a scene. Our contribution is to fuse the semantic richness of text with the expressivity of sketch, to create a hybrid ‘semantic sketch ’ based video retrieval system. Trajec-tory extraction and clustering are applied to pre-process each clip into a video object representation that we augment with object classification and colour infor-mation. The result is a system capable of searching videos based on the desired colour, motion path, and semantic labels of the objects present. We evaluate the performance of our system over the TSF dataset of broadcast sports footage. 1
Keyphrases
free-hand sketch video retrieval using object semantics desired colour semantic richness pictorial representation motion path broadcast sport footage video retrieval system semantic label colour infor-mation im-precise vehicle trajec-tory extraction video object representation tsf dataset object type video retrieval hybrid semantic sketch novel video retrieval system object classification
