Storyboard sketches for content based video retrieval

We present a novel Content Based Video Retrieval (CBVR) system, driven by free-hand sketch queries depicting both objects and their movement (via dynamic cues; streak-lines and arrows). Our main contribution is a probabilistic model of video clips (based on Linear Dynamical Systems), leading to an a...

Full description

Bibliographic Details
Main Authors: Collomosse, J, McNeill, G, Qian, Y
Format: Conference item
Published: Institute of Electrical and Electronics Engineers 2010
_version_ 1797070640727982080
author Collomosse, J
McNeill, G
Qian, Y
author_facet Collomosse, J
McNeill, G
Qian, Y
author_sort Collomosse, J
collection OXFORD
description We present a novel Content Based Video Retrieval (CBVR) system, driven by free-hand sketch queries depicting both objects and their movement (via dynamic cues; streak-lines and arrows). Our main contribution is a probabilistic model of video clips (based on Linear Dynamical Systems), leading to an algorithm for matching descriptions of sketched objects to video. We demonstrate our model fitting to clips under static and moving camera conditions, exhibiting linear and oscillatory motion. We evaluate retrieval on two real video data sets, and on a video data set exhibiting controlled variation in shape, color, motion and clutter.
first_indexed 2024-03-06T22:41:49Z
format Conference item
id oxford-uuid:5bd5861c-ff0f-40fd-ab95-525975a351b5
institution University of Oxford
last_indexed 2024-03-06T22:41:49Z
publishDate 2010
publisher Institute of Electrical and Electronics Engineers
record_format dspace
spelling oxford-uuid:5bd5861c-ff0f-40fd-ab95-525975a351b52022-03-26T17:24:24ZStoryboard sketches for content based video retrievalConference itemhttp://purl.org/coar/resource_type/c_5794uuid:5bd5861c-ff0f-40fd-ab95-525975a351b5Symplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2010Collomosse, JMcNeill, GQian, YWe present a novel Content Based Video Retrieval (CBVR) system, driven by free-hand sketch queries depicting both objects and their movement (via dynamic cues; streak-lines and arrows). Our main contribution is a probabilistic model of video clips (based on Linear Dynamical Systems), leading to an algorithm for matching descriptions of sketched objects to video. We demonstrate our model fitting to clips under static and moving camera conditions, exhibiting linear and oscillatory motion. We evaluate retrieval on two real video data sets, and on a video data set exhibiting controlled variation in shape, color, motion and clutter.
spellingShingle Collomosse, J
McNeill, G
Qian, Y
Storyboard sketches for content based video retrieval
title Storyboard sketches for content based video retrieval
title_full Storyboard sketches for content based video retrieval
title_fullStr Storyboard sketches for content based video retrieval
title_full_unstemmed Storyboard sketches for content based video retrieval
title_short Storyboard sketches for content based video retrieval
title_sort storyboard sketches for content based video retrieval
work_keys_str_mv AT collomossej storyboardsketchesforcontentbasedvideoretrieval
AT mcneillg storyboardsketchesforcontentbasedvideoretrieval
AT qiany storyboardsketchesforcontentbasedvideoretrieval