Human Action Recognition in Unconstrained Videos by Explicit Motion Modeling

Human action recognition in unconstrained videos is a challenging problem with many applications. Most state-of-the-art approaches adopted the well-known bag-of-features representations, generated based on isolated local patches or patch trajectories, where motion patterns, such as object-object and...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2015-11, Vol.24 (11), p.3781-3795
Main Authors: Jiang, Yu-Gang, Dai, Qi, Liu, Wei, Xue, Xiangyang, Ngo, Chong-Wah
Format: Article
Language:English
Subjects:
Algorithms
Benchmark testing
camera motion
Cameras
Human action recognition
Human motion
Humans
Image Processing, Computer-Assisted - methods
Mathematical analysis
Modelling
motion representation
Movement
Movements
Moving object recognition
Pattern Recognition, Automated - methods
reference points
Representations
Shape
Tracking
Trajectories
Trajectory
Transaction processing
Video Recording - methods
Videos
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Human action recognition in unconstrained videos is a challenging problem with many applications. Most state-of-the-art approaches adopted the well-known bag-of-features representations, generated based on isolated local patches or patch trajectories, where motion patterns, such as object-object and object-background relationships are mostly discarded. In this paper, we propose a simple representation aiming at modeling these motion relationships. We adopt global and local reference points to explicitly characterize motion information, so that the final representation is more robust to camera movements, which widely exist in unconstrained videos. Our approach operates on the top of visual codewords generated on dense local patch trajectories, and therefore, does not require foreground-background separation, which is normally a critical and difficult step in modeling object relationships. Through an extensive set of experimental evaluations, we show that the proposed representation produces a very competitive performance on several challenging benchmark data sets. Further combining it with the standard bag-of-features or Fisher vector representations can lead to substantial improvements.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2015.2456412