no code implementations • 30 Jan 2023 • Ali Farajzadeh Bavil, Hamed Damirchi, Hamid D. Taghirad
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
1 code implementation • 23 Oct 2022 • Pedram Agand, Mo Chen, Hamid D. Taghirad
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.
no code implementations • 19 Oct 2022 • Pouria Mehrabi, Hamid D. Taghirad
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.
no code implementations • 16 Dec 2021 • M. Reza J. Harandi, Hamid D. Taghirad
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.
no code implementations • 1 Dec 2021 • Pouria Mehrabi, Hamid D. Taghirad
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.
no code implementations • 1 Jul 2021 • Hamed Damirchi, Rooholla Khorrambakht, Hamid D. Taghirad, Behzad Moshiri
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.
no code implementations • 6 Apr 2021 • M. Reza J. Harandi, Amir Molaei, Hamid D. Taghirad, Jose Guadalupe Romero
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.
no code implementations • 28 Mar 2021 • Faraz Lotfi, Hamid D. Taghirad
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.
no code implementations • 24 Mar 2021 • Faraz Lotfi, Farnoosh Faraji, Hamid D. Taghirad
Object localization has a vital role in any object detector, and therefore, has been the focus of attention by many researchers.
no code implementations • 24 Mar 2021 • Faraz Lotfi, Hamid D. Taghirad
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.
no code implementations • 1 Jan 2021 • Pedram Agand, Mo Chen, Hamid D. Taghirad
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.
no code implementations • 30 Nov 2020 • M. Reza J. Harandi, Hamid D. Taghirad
Finding a suitable desired inertia matrix as the solution of nonlinear PDEs related to kinetic energy shaping is a challenging problem.
no code implementations • 17 Nov 2020 • Hamed Damirchi, Rooholla Khorrambakht, Hamid D. Taghirad
Visual odometry networks commonly use pretrained optical flow networks in order to derive the ego-motion between consecutive frames.