A Robust and Scalable Visual Category and Action Recognition System using Kernel Discriminant Analysis with Spectral Regression

Tahir, Muhammad, Yan, Fei, Koniusz, Peter, Awais, Muhammad, Barnard, Mark, Mikolajczyk, Krystian, Bouridane, Ahmed and Kittler, Josef (2013) A Robust and Scalable Visual Category and Action Recognition System using Kernel Discriminant Analysis with Spectral Regression. IEEE Transactions on Multimedia, 15 (7). pp. 1653-1664. ISSN 1520-9210

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.1109/TMM.2013.2264927

Abstract

Visual concept detection and action recognition are one of the most important tasks in content-based multimedia information retrieval (CBMIR) technology. It aims at annotating images using a vocabulary defined by a set of concepts of interest including scenes types (mountains, snow etc) or human actions (phoning, playing instrument). This paper describes our system in the ImageCLEF@ICPR10, Pascal VOC 08 Visual Concept Detection and Pascal VOC 10 Action Recognition Challenges. The proposed system ranked first in these large-scale tasks when evaluated independently by the organizers. The proposed system involves stateof- the-art local descriptor computation, vector quantisation via clustering, structured scene or object representation via localised histograms of vector codes, similarity measure for kernel construction and classifier learning. The main novelty is the classifierlevel and kernel-level fusion using Kernel Discriminant Analysis and Spectral Regression (SR-KDA) with RBF Chi-Squared kernels obtained from various image descriptors. The distinctiveness of the proposed method is also assessed experimentally using a video benchmark: the Mediamill Challenge along with benchmarks from ImageCLEF@ICPR10, Pascal VOC 10 and Pascal VOC 08. From the experimental results, it can be derived that the presented system consistently yields significant performance gains when compared with the state-of-the art methods. The other strong point is the introduction of SR-KDA in the classification stage where the time complexity scales linearly with respect to the number of concepts and the main computational complexity is independent of the number of categories.

Item Type: Article
Uncontrolled Keywords: Action recognition from still images, SIFT, kernel discriminant analysis, visual category recognition
Subjects: H600 Electronic and Electrical Engineering
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Ellen Cole
Date Deposited: 20 Sep 2013 13:16
Last Modified: 13 Oct 2019 00:32
URI: http://nrl.northumbria.ac.uk/id/eprint/13559

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics