Show simple item record

dc.contributor.authorTakáč, Martin
dc.contributor.authorAhipaşaoğlu, Selin Damla
dc.contributor.authorCheung, Ngai-Man
dc.contributor.authorRichtarik, Peter
dc.date.accessioned2019-03-14T14:23:55Z
dc.date.available2019-03-14T14:23:55Z
dc.date.issued2019-02-14
dc.identifier.citationTakáč M, Ahipaşaoğlu SD, Cheung N-M, Richtárik P (2019) TopSpin: TOPic Discovery via Sparse Principal Component INterference. Research on Intelligent Manufacturing: 157–180. Available: http://dx.doi.org/10.1007/978-3-030-12119-8_8.
dc.identifier.issn2523-3386
dc.identifier.issn2523-3394
dc.identifier.doi10.1007/978-3-030-12119-8_8
dc.identifier.urihttp://hdl.handle.net/10754/631654
dc.description.abstractWe propose a novel topic discovery algorithm for unlabeled images based on the bag-of-words (BoW) framework. We first extract a dictionary of visual words and subsequently for each image compute a visual word occurrence histogram. We view these histograms as rows of a large matrix from which we extract sparse principal components (PCs). Each PC identifies a sparse combination of visual words which co-occur frequently in some images but seldom appear in others. Each sparse PC corresponds to a topic, and images whose interference with the PC is high belong to that topic, revealing the common parts possessed by the images. We propose to solve the associated sparse PCA problems using an Alternating Maximization (AM) method, which we modify for the purpose of efficiently extracting multiple PCs in a deflation scheme. Our approach attacks the maximization problem in SPCA directly and is scalable to high-dimensional data. Experiments on automatic topic discovery and category prediction demonstrate encouraging performance of our approach. Our SPCA solver is publicly available.
dc.description.sponsorshipThis work was partially supported by the U.S. National Science Foundation, under award number NSF:CCF:1618717, NSF:CMMI:1663256 and NSF:CCF:1740796.
dc.publisherSpringer Nature
dc.relation.urlhttp://link.springer.com/chapter/10.1007/978-3-030-12119-8_8
dc.relation.urlhttp://arxiv.org/pdf/1311.1406
dc.rightsArchived with thanks to Springer International Publishing
dc.subjectSparse PCA
dc.subjectBag-of-words
dc.subjectTopic discovery
dc.subjectHidden topic
dc.titleTopSpin: TOPic Discovery via Sparse Principal Component INterference
dc.typeBook Chapter
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.identifier.journalBrain-Inspired Intelligence and Visual Perception
dc.eprint.versionPre-print
dc.contributor.institutionLehigh University, Bethlehem, USA
dc.contributor.institutionSingapore University of Technology and Design, Singapore, Singapore
dc.contributor.institutionMoscow Institute of Physics and Technology, Dolgoprudny, Russia
dc.contributor.institutionUniversity of Edinburgh, Edinburgh, UK
dc.identifier.arxivid1311.1406
kaust.personRichtarik, Peter
refterms.dateFOA2019-12-09T12:09:29Z
dc.date.published-online2019-02-15
dc.date.published-print2019


Files in this item

Thumbnail
Name:
OriginalPaperfile1.pdf
Size:
4.024Mb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record