A Correlation Based Feature Representation for First-Person Activity Recognition

11/15/2017
by   Reza Kahani, et al.
0

In this paper, a simple yet efficient feature encoding for first-person video is introduced. The proposed method is appropriate for representation of high-dimensional features such as those extracted from convolutional neural networks (CNNs). The per-frame extracted features are considered as a set of time series, and inter and intra-time series relations are employed to represent the video descriptors. To find the inter-time relations, the series are grouped and the linear correlation between each pair of groups is calculated. The relations between them can represent the scene dynamics and local motions. The introduced grouping strategy helps to considerably reduce the computational cost. Furthermore, we split the series in temporal direction in order to better focus on each local time window. In order to extract the cyclic motion patterns, which can be considered as primary components of various activities, intra-time series correlations are exploited. The representation method results in highly discriminative features which can be simply classified by a linear SVM. The experiments show that our method outperforms the previous encoding methods, such as bag of visual word (BoVW), improved Fisher vector (IFV), Fourier temporal pyramid (FTP), and recently proposed pooled time series (PoT) on three public first-person datasets. The experimental results also confirm that the proposed method has a superior performance over the state-of-the-art methods on recognizing first-person activities

READ FULL TEXT
research
12/19/2014

Pooled Motion Features for First-Person Videos

In this paper, we present a new feature representation for first-person ...
research
06/06/2016

Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach

In this paper, we present an end-to-end approach to simultaneously learn...
research
10/28/2014

A Short Image Series Based Scheme for Time Series Digital Image Correlation

A new scheme for digital image correlation, i.e., short time series DIC ...
research
02/19/2018

Learning Representative Temporal Features for Action Recognition

In this paper we present a novel video classification methodology that a...
research
07/24/2020

ESPRESSO: Entropy and ShaPe awaRe timE-Series SegmentatiOn for processing heterogeneous sensor data

Extracting informative and meaningful temporal segments from high-dimens...
research
02/16/2022

HDC-MiniROCKET: Explicit Time Encoding in Time Series Classification with Hyperdimensional Computing

Classification of time series data is an important task for many applica...
research
12/11/2012

Bag-of-Words Representation for Biomedical Time Series Classification

Automatic analysis of biomedical time series such as electroencephalogra...

Please sign up or login with your details

Forgot password? Click here to reset