Encoding spatio-temporal distribution by generalized VLAD for action recognition

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

2 Scopus citations

Abstract

The location information of interest points is an important cue for action recognition. In order to model the spatio-temporal distribution, we propose a novel position feature which is constructed by normalized pairwise relative positions of points. Promising performance has been achieved by Vector of Locally Aggregated Descriptors (VLAD) which gather the differences between descriptors and visual words. However, original VLAD imposes equal weights for difference vectors and ignores zero-order statistics of local descriptors. In this paper, we present Generalized VLAD (GVLAD), an extension of VLAD to encode the position features as well as local appearance descriptors, by which different weights and zero-order information are simultaneously taken into consideration. The state-of-the-art performance on two benchmark datasets validates the effectiveness of our proposed method.

Original languageEnglish
Title of host publication2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering, CCECE 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages620-625
Number of pages6
EditionJune
ISBN (Electronic)9781479958276
DOIs
StatePublished - 19 Jun 2015
Externally publishedYes
Event2015 28th IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2015 - Halifax, Canada
Duration: 3 May 20156 May 2015

Publication series

NameCanadian Conference on Electrical and Computer Engineering
NumberJune
Volume2015-June
ISSN (Print)0840-7789

Conference

Conference2015 28th IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2015
Country/TerritoryCanada
CityHalifax
Period3/05/156/05/15

Fingerprint

Dive into the research topics of 'Encoding spatio-temporal distribution by generalized VLAD for action recognition'. Together they form a unique fingerprint.

Cite this