Complex Event Recognition Using Constrained Low-Rank Representation

Keywords

Action concepts; Activity recognition; Complex event recognition; Low-rank optimization

Abstract

Complex event recognition is the problem of recognizing events in long and unconstrained videos. In this extremely challenging task, concepts have recently shown a promising direction where core low-level events (referred to as concepts) are annotated and modeled using a portion of the training data, then each complex event is described using concept scores, which are features representing the occurrence confidence for the concepts in the event. However, because of the complex nature of the videos, both the concept models and the corresponding concept scores are significantly noisy. In order to address this problem, we propose a novel low-rank formulation, which combines the precisely annotated videos used to train the concepts, with the rich concept scores. Our approach finds a new representation for each event, which is not only low-rank, but also constrained to adhere to the concept annotation, thus suppressing the noise, and maintaining a consistent occurrence of the concepts in each event. Extensive experiments on large scale real world dataset TRECVID Multimedia Event Detection 2011 and 2012 demonstrate that our approach consistently improves the discriminativity of the concept scores by a significant margin.

Publication Date

8-19-2015

Publication Title

Image and Vision Computing

Volume

42

Number of Pages

13-21

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1016/j.imavis.2015.06.007

Socpus ID

84939503642 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/84939503642

This document is currently not available here.

Share

COinS