Authors:
Pau Agustí
;
V. Javier Traver
;
Filiberto Pla
and
Raúl Montoliu
Affiliation:
Jaume-I University, Spain
Keyword(s):
Clustering, Human Action Recognition, Random Projections, Bag-of-Words.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Features Extraction
;
Image and Video Analysis
Abstract:
During the last years, the bag-of-words (BoW) approach has become quite popular for representing actions from video sequences. While the BoW is conceptually very simple and practically effective, it suffers from some drawbacks. In particular, the quantization procedure behind the BoW usually relies on a computationally heavy k-means clustering. In this work we explore whether alternative approaches as simple as random projections, which are data agnostic, can represent a practical alternative. Results reveal that this randomized quantization offers an interesting computational-accuracy trade-off, because although recognition performance is not yet as high as with k-means, it is still competitive with an speed-up higher than one order of magnitude.