Sampling-based methods for motion planning with constraints
Robots with many degrees of freedom (eg, humanoid robots and mobile manipulators) have
increasingly been employed to accomplish realistic tasks in domains such as disaster relief …
increasingly been employed to accomplish realistic tasks in domains such as disaster relief …
Linear cross-modal hashing for efficient multimedia search
Most existing cross-modal hashing methods suffer from the scalability issue in the training
phase. In this paper, we propose a novel cross-modal hashing approach with a linear time …
phase. In this paper, we propose a novel cross-modal hashing approach with a linear time …
Jensen-bregman logdet divergence with application to efficient similarity search for covariance matrices
Covariance matrices have found success in several computer vision applications, including
activity recognition, visual surveillance, and diffusion tensor imaging. This is because they …
activity recognition, visual surveillance, and diffusion tensor imaging. This is because they …
Hashing on nonlinear manifolds
Learning-based hashing methods have attracted considerable attention due to their ability to
greatly increase the scale at which existing algorithms may operate. Most of these methods …
greatly increase the scale at which existing algorithms may operate. Most of these methods …
Path planning under kinematic constraints by rapidly exploring manifolds
The situation arising in path planning under kinematic constraints, where the valid
configurations define a manifold embedded in the joint ambient space, can be seen as a …
configurations define a manifold embedded in the joint ambient space, can be seen as a …
Advances in matrix manifolds for computer vision
YM Lui - Image and Vision Computing, 2012 - Elsevier
The attention paid to matrix manifolds has grown considerably in the computer vision
community in recent years. There are a wide range of important applications including face …
community in recent years. There are a wide range of important applications including face …
Efficient similarity search for covariance matrices via the Jensen-Bregman LogDet divergence
Covariance matrices provide compact, informative feature descriptors for use in several
computer vision applications, such as people-appearance tracking, diffusion-tensor imaging …
computer vision applications, such as people-appearance tracking, diffusion-tensor imaging …
A fast approximate nearest neighbor search algorithm in the hamming space
MM Esmaeili, RK Ward… - IEEE transactions on …, 2012 - ieeexplore.ieee.org
A fast approximate nearest neighbor search algorithm for the (binary) Hamming space is
proposed. The proposed Error Weighted Hashing (EWH) algorithm is up to 20 times faster …
proposed. The proposed Error Weighted Hashing (EWH) algorithm is up to 20 times faster …
Tangent bundles on special manifolds for action recognition
YM Lui - IEEE Transactions on Circuits and Systems for Video …, 2011 - ieeexplore.ieee.org
Increasingly, machines are interacting with people through human action recognition from
video streams. Video data can naturally be represented as a third-order data tensor …
video streams. Video data can naturally be represented as a third-order data tensor …