Discovery - University of Dundee - Online Publications

Library & Learning Centre

Human action recognition by random features and hand-crafted features

Human action recognition by random features and hand-crafted features: a comparative study

Research output: Chapter in Book/Report/Conference proceedingConference contribution

View graph of relations

Authors

Research units

Info

Original languageEnglish
Title of host publicationComputer Vision - ECCV 2014 Workshops
Subtitle of host publicationZurich, Switzerland, September 6-7 and 12, 2014, Proceedings, Part II
EditorsLourdes Agapito , Michael M. Bronstein, Carsten Rother
Pages14-28
Number of pages15
ISBN (Electronic)9783319161815
DOIs
StatePublished - 2015
Event6th International Workshop on Video Event Categorization, Tagging and Retrieval towards Big Data - Zurich, Switzerland

Publication series

NameLecture notes in computer science
Volume8926
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Workshop

Workshop6th International Workshop on Video Event Categorization, Tagging and Retrieval towards Big Data
Abbreviated titleVECTaR 2014
CountrySwitzerland
CityZurich
Period6/09/146/09/14
OtherPart of 13th European Conference on Computer Vision, ECCV 2014
Internet address

Abstract

One popular approach for human action recognition is to extract features from videos as representations, subsequently followed by a classification procedure of the representations. In this paper, we investigate and compare hand-crafted and random feature representation for human action recognition on YouTube dataset. The former is built on 3D HoG/HoF and SIFT descriptors while the latter bases on random projection. Three encoding methods: Bag of Feature(BoF), Sparse Coding(SC) and VLAD are adopted. Spatial temporal pyramid and a twolayer SVM classifier are employed for classification. Our experiments demonstrate that: 1) Sparse Coding is confirmed to outperform Bag of Feature; 2) Using a model of hybrid features incorporating framestatic can significantly improve the overall recognition accuracy; 3) The frame-static features works surprisingly better than motion features only; 4) Compared with the success of hand-crafted feature representation, the random feature representation does not perform well in this dataset.

Documents

DOI

Library & Learning Centre

Contact | Accessibility | Policy