Topic level sampling towards optimized locality sensitive vocabulary coding

Jie Chen*, Ling Yu Duan, Bing Li, Rongrong Ji, Wen Gao

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We propose a novel locality sensitive vocabulary coding scheme to extract compact descriptors for low bit rate visual search. We employ Latent Dirichlet Allocation (LDA) to learn the topic vocabularies of lower dimension to generate compact descriptors. To deal with diverse datasets, LDA model is introduced to subdivide a dataset into groups of images with a topic model, where the code word distributions in each group produce coherent statistics from generative learning. Moreover, our empirical study has shown that the original Bag-of-Word (BoW) is sparse, and the occurrences of non-zero words is coherent within a topic. Our proposed topic-wise vocabulary learning yields a more compact yet discriminative codebook to search images. Given a query image, multiple topics are determined, which is fed into the topic vocabularies to generate more compact topical descriptor. Comparison experiments show our topic-wise locality sensitive vocabulary coding produces more compact and discriminative descriptors than the state-of-the-arts.

Original languageEnglish
Title of host publicationICICS 2011 - 8th International Conference on Information, Communications and Signal Processing
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event8th International Conference on Information, Communications and Signal Processing, ICICS 2011 - Singapore, Singapore
Duration: 13 Dec 201116 Dec 2011

Publication series

NameICICS 2011 - 8th International Conference on Information, Communications and Signal Processing

Conference

Conference8th International Conference on Information, Communications and Signal Processing, ICICS 2011
Country/TerritorySingapore
CitySingapore
Period13/12/1116/12/11

Keywords

  • Compact visual descriptor
  • mobile search
  • topic model

Fingerprint

Dive into the research topics of 'Topic level sampling towards optimized locality sensitive vocabulary coding'. Together they form a unique fingerprint.

Cite this