English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Topic models for semantics-preserving video compression

Wanke, J., Ulges, A., Lampert, C., & Breuel, T. (2010). Topic models for semantics-preserving video compression. In J. Wang, N. Boujemaa, N. Ramirez, & A. Natsev (Eds.), MIR '10: Proceedings of the international conference on Multimedia information retrieval (pp. 275-284). New York, NY, USA: ACM Press.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0002-94D8-3 Version Permalink: http://hdl.handle.net/21.11116/0000-0002-94D9-2
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Wanke, J, Author
Ulges, A, Author
Lampert, CH1, 2, Author              
Breuel, TM, Author
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Most state-of-the-art systems for content-based video understanding tasks require video content to be represented as collections of many low-level descriptors, e.g. as histograms of the color, texture or motion in local image regions. In order to preserve as much of the information contained in the original video as possible, these representations are typically high-dimensional, which conflicts with the aim for compact descriptors that would allow better efficiency and lower storage requirements. In this paper, we address the problem of semantic compression of video, i.e. the reduction of low-level descriptors to a small number of dimensions while preserving most of the semantic information. For this, we adapt topic models - which have previously been used as compact representations of still images - to take into account the temporal structure of a video, as well as multi-modal components such as motion information. Experiments on a large-scale collection of YouTube videos show that we can achieve a compression ratio of 20 : 1 compared to ordinary histogram representations and at least 2 : 1 compared to other dimensionality reduction techniques without significant loss of prediction accuracy. Also, improvements are demonstrated for our video-specific extensions modeling temporal structure and multiple modalities.

Details

show
hide
Language(s):
 Dates: 2010-03
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: DOI: 10.1145/1743384.1743433
 Degree: -

Event

show
hide
Title: 2010 ACM SIGMM International Conference on Multimedia Information Retrieval (MIR 2010)
Place of Event: Philadelphia, PA, USA
Start-/End Date: 2010-03-29 - 2010-03-31

Legal Case

show

Project information

show

Source 1

show
hide
Title: MIR '10: Proceedings of the international conference on Multimedia information retrieval
Source Genre: Proceedings
 Creator(s):
Wang, JZ, Editor
Boujemaa, N, Editor
Ramirez, NO, Editor
Natsev, A, Editor
Affiliations:
-
Publ. Info: New York, NY, USA : ACM Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 275 - 284 Identifier: ISBN: 978-1-60558-815-5