Title

Recognition Of Complex Events: Exploiting Temporal Dynamics Between Underlying Concepts

Keywords

Complex Event Recognition; Hankel Matrices; Harmonic signatures; Linear Dynamical Systems; Subspace state identification; Temporal Representation; TRECVID MED

Abstract

While approaches based on bags of features excel at low-level action classification, they are ill-suited for recognizing complex events in video, where concept-based temporal representations currently dominate. This paper proposes a novel representation that captures the temporal dynamics of windowed mid-level concept detectors in order to improve complex event recognition. We first express each video as an ordered vector time series, where each time step consists of the vector formed from the concatenated confidences of the pre-trained concept detectors. We hypothesize that the dynamics of time series for different instances from the same event class, as captured by simple linear dynamical system (LDS) models, are likely to be similar even if the instances differ in terms of low-level visual features. We propose a two-part representation composed of fusing: (1) a singular value decomposition of block Hankel matrices (SSID-S) and (2) a harmonic signature (HS) computed from the corresponding eigen-dynamics matrix. The proposed method offers several benefits over alternate approaches: our approach is straightforward to implement, directly employs existing concept detectors and can be plugged into linear classification frameworks. Results on standard datasets such as NIST's TRECVID Multimedia Event Detection task demonstrate the improved accuracy of the proposed method.

Publication Date

9-24-2014

Publication Title

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Number of Pages

2243-2250

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/CVPR.2014.287

Socpus ID

84911400185 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/84911400185

This document is currently not available here.

Share

COinS