Title
Multi-view action recognition using bag-of-words and various fusion schemes
Author
Burghouts, G.J.
Eendebak, P.T.
Bouma, H.
Hove, R.J.M.
Publication year
2014
Abstract
In this paper, we summarize how the action recognition can be improved when multiple views are available. The novelty is that we explore various combination schemes within the robust and simple bag-of-words (BoW) framework, from early fusion of features to late fusion of multiple classifiers. In new experiments on the publicly available IXMAS dataset, we learn that action recognition can be improved significantly already by only adding one viewpoint. We demonstrate that the state-of-the-art on this dataset can be improved by 5% – achieving 96.4% accuracy – when multiple views are combined.
Subject
Physics & Electronics
II - Intelligent Imaging
TS - Technical Sciences
Safety and Security
Image processing
Defence, Safety and Security
Action recognition
Video images
Bag of words
Multiple views
To reference this document use:
http://resolver.tudelft.nl/uuid:0abe327d-05b7-4bcd-be32-1c41e4f6025c
TNO identifier
489757
Source
Netherlands Conference on Computer Vision NCCV 2014, 24-25 April 2014, Ermelo, The Netherlands, 1-2
Document type
conference paper