Action recognition using rate-invariant analysis of skeletal shape trajectories
BB Amor, J Su, A Srivastava - IEEE transactions on pattern …, 2015 - ieeexplore.ieee.org
We study the problem of classifying actions of human subjects using depth movies
generated by Kinect or other depth sensors. Representing human body as dynamical …
generated by Kinect or other depth sensors. Representing human body as dynamical …
Canonical time warping for alignment of human behavior
Alignment of time series is an important problem to solve in many scientific disciplines. In
particular, temporal alignment of two or more subjects performing similar activities is a …
particular, temporal alignment of two or more subjects performing similar activities is a …
Generalized time warping for multi-modal alignment of human motion
F Zhou, F De la Torre - 2012 IEEE Conference on Computer …, 2012 - ieeexplore.ieee.org
Temporal alignment of human motion has been a topic of recent interest due to its
applications in animation, telerehabilitation and activity recognition among others. This …
applications in animation, telerehabilitation and activity recognition among others. This …
Generalized canonical time warping
F Zhou, F De la Torre - IEEE transactions on pattern analysis …, 2015 - ieeexplore.ieee.org
Temporal alignment of human motion has been of recent interest due to its applications in
animation, tele-rehabilitation and activity recognition. This paper presents generalized …
animation, tele-rehabilitation and activity recognition. This paper presents generalized …
Mining the home environment
DJ Cook, N Krishnan - Journal of intelligent information systems, 2014 - Springer
Individuals spend a majority of their time in their home or workplace and for many, these
places are our sanctuaries. As society and technology advance there is a growing interest in …
places are our sanctuaries. As society and technology advance there is a growing interest in …
Automatic analysis of facial expressions based on deep covariance trajectories
In this article, we propose a new approach for facial expression recognition (FER) using
deep covariance descriptors. The solution is based on the idea of encoding local and global …
deep covariance descriptors. The solution is based on the idea of encoding local and global …
Human activity prediction using temporally-weighted generalized time warping
Different from traditional human activity recognition, human activity prediction aims to
recognize an unfinished activity, typically in absence of explicit temporal progress status. In …
recognize an unfinished activity, typically in absence of explicit temporal progress status. In …
Action representations in robotics: A taxonomy and systematic classification
Understanding and defining the meaning of “action” is substantial for robotics research. This
becomes utterly evident when aiming at equipping autonomous robots with robust …
becomes utterly evident when aiming at equipping autonomous robots with robust …
Sparse canonical temporal alignment with deep tensor decomposition for action recognition
In this paper, we solve three problems in action recognition: sub-action, multi-subject, and
multi-modality, by reducing the diversity of intra-class samples. The main stage contains …
multi-modality, by reducing the diversity of intra-class samples. The main stage contains …
Fitting, comparison, and alignment of trajectories on positive semi-definite matrices with application to action recognition
In this paper, we tackle the problem of action recognition using body skeletons extracted
from video sequences. Our approach lies in the continuity of recent works representing …
from video sequences. Our approach lies in the continuity of recent works representing …