Change search
ReferencesLink to record
Permanent link

Direct link
How to Supervise Topic Models
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. (CVAP)ORCID iD: 0000-0002-8640-9370
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.ORCID iD: 0000-0002-5750-9655
2014 (English)In: Computer Vision - ECCV 2014 Workshops: Zurich, Switzerland, September 6-7 and 12, 2014, Proceedings, Part II / [ed] Agapito, Bronstein, Rother, Zurich: Springer Publishing Company, 2014, 500-515 p.Chapter in book (Refereed)
Abstract [en]

Supervised topic models are important machine learning tools whichhave been widely used in computer vision as well as in other domains. However,there is a gap in the understanding of the supervision impact on the model. Inthis paper, we present a thorough analysis on the behaviour of supervised topicmodels using Supervised Latent Dirichlet Allocation (SLDA) and propose twofactorized supervised topic models, which factorize the topics into signal andnoise. Experimental results on both synthetic data and real-world data for computer vision tasks show that supervision need to be boosted to be effective andfactorized topic models are able to enhance the performance.

Place, publisher, year, edition, pages
Zurich: Springer Publishing Company, 2014. 500-515 p.
Keyword [en]
Topic Modeling, SLDA, LDA, Factorized Supervised Topic Models
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computer Science
URN: urn:nbn:se:kth:diva-152691DOI: 10.1007/978-3-319-16181-5_39ISI: 000362495500039ScopusID: 2-s2.0-84928801474ISBN: 978-3-319-16181-5OAI: diva2:751417
European Conference on Computer Vision (ECCVws 2014, GMCV),Zurich, September 6-12, 2014
Swedish Research Council

QC 20141024

Available from: 2014-10-01 Created: 2014-10-01 Last updated: 2015-11-03Bibliographically approved

Open Access in DiVA

ECCVws(1972 kB)37 downloads
File information
File name FULLTEXT01.pdfFile size 1972 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopusConference websiteThe final publication is available at

Search in DiVA

By author/editor
Zhang, ChengKjellström, Hedvig
By organisation
Computer Vision and Active Perception, CVAP
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 37 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 104 hits
ReferencesLink to record
Permanent link

Direct link