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...
Main Authors: | , , |
---|---|
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 |