no code implementations • 22 Aug 2023 • Soubarna Banik, Edvard Avagyan, Alejandro Mendoza Gracia, Alois Knoll
Existing kinematic skeleton-based 3D human pose estimation methods only predict joint positions.
no code implementations • 24 Apr 2023 • Soubarna Banik, Patricia Gschoßmann, Alejandro Mendoza Garcia, Alois Knoll
We show that our proposed method compares favorably with the state-of-the-art (SoA).
no code implementations • 11 Mar 2022 • Marco Oliva, Soubarna Banik, Josip Josifovski, Alois Knoll
We derive a graph representation that models the physical structure of the manipulator and combines the robot's internal state with a low-dimensional description of the visual scene generated by an image encoding network.
no code implementations • 23 Aug 2021 • Soubarna Banik, Alejandro Mendoza Garcia, Lorenz Kiwull, Steffen Berweck, Alois Knoll
We evaluate it on our rehab datasets, and observe that the performance degrades significantly from non-rehab to rehab, highlighting the need for these datasets.
1 code implementation • 21 May 2021 • Soubarna Banik, Alejandro Mendoza Gracia, Alois Knoll
We propose one such graph convolutional network named PoseGraphNet for 3D human pose regression from 2D poses.
Ranked #201 on 3D Human Pose Estimation on Human3.6M
no code implementations • 10 Nov 2018 • Soubarna Banik, Mikko Lauri, Simone Frintrop
With this inspiration, a deep convolutional neural network for low-level object attribute classification, called the Deep Attribute Network (DAN), is proposed.