Search Results for author:
Found 13 papers, 1 papers with code
Action Capsules: Human Skeleton Action Recognition
Due to the compact and rich high-level representations offered, skeleton-based human action recognition has recently become a highly active research topic.
Ranked #4 on
Skeleton Based Action Recognition
on N-UCLA
Online Probabilistic Model Identification using Adaptive Recursive MCMC
We suggest the Adaptive Recursive Markov Chain Monte Carlo (ARMCMC) method, which eliminates the shortcomings of conventional online techniques while computing the entire probability density function of model parameters.
A Segment-Wise Gaussian Process-Based Ground Segmentation With Local Smoothness Estimation
Simulation results show the effectiveness of the proposed method to give a continuous and precise estimation of the ground surface in rough and bumpy scenes while being fast enough for real-world applications.
Reformulation of Matching Equation in Potential Energy Shaping
Interconnection and damping assignment passivity-based control is an approach based on total energy shaping by assigning desired kinetic and potential energy to the system.
A Novel Gaussian Process Based Ground Segmentation Algorithm with Local-Smoothness Estimation
The log-marginal likelihood function is assumed to be a multi-task objective function, to represent a whole-frame unbiased view of the ground at each frame.
A Consistency-Based Loss for Deep Odometry Through Uncertainty Propagation
In such cases where multiple losses are imposed on a network, the uncertainty over each output can be derived to weigh the different loss terms in a maximum likelihood setting.
Bounded Inputs Total Energy Shaping for Mechanical Systems
However, actuator saturation is typically neglected in the design of control systems, with compensation being made in the form of over-designing the actuator or by post-analyzing the resulting system to ensure acceptable performance.
Single Object Tracking through a Fast and Effective Single-Multiple Model Convolutional Neural Network
Recent state-of-the-art (SOTA) approaches are proposed based on taking a matching network with a heavy structure to distinguish the target from other objects in the area which indeed drastically downgrades the performance of the tracker in terms of speed.
Object Localization Through a Single Multiple-Model Convolutional Neural Network with a Specific Training Approach
Object localization has a vital role in any object detector, and therefore, has been the focus of attention by many researchers.
A Framework for 3D Tracking of Frontal Dynamic Objects in Autonomous Cars
Both recognition and 3D tracking of frontal dynamic objects are crucial problems in an autonomous vehicle, while depth estimation as an essential issue becomes a challenging problem using a monocular camera.
ARMCMC: ONLINE MODEL PARAMETERS DENSITY ESTIMATION IN BAYESIAN PARADIGM
We demonstrate our approach on a challenging benchmark: estimation of parameters in the Hunt-Crossley dynamic model, which models both on/off contact forces applied to soft materials.
On the Matching Equations of Kinetic Energy Shaping in IDA-PBC
Finding a suitable desired inertia matrix as the solution of nonlinear PDEs related to kinetic energy shaping is a challenging problem.
Exploring Self-Attention for Visual Odometry
Visual odometry networks commonly use pretrained optical flow networks in order to derive the ego-motion between consecutive frames.
