no code implementations • 2 Feb 2024 • Ivanna Kramer, Vinzent Rittel, Lara Blomenkamp, Sabine Bauer, Dietrich Paulus
Vertebral morphological measurements are important across various disciplines, including spinal biomechanics and clinical applications, pre- and post-operatively.
no code implementations • 14 Jan 2024 • Viktor Seib, Malte Roosen, Ida Germann, Stefan Wirtz, Dietrich Paulus
Creating annotated datasets demands a substantial amount of manual effort.
1 code implementation • 13 Oct 2021 • Christian Korbach, Markus D. Solbach, Raphael Memmesheimer, Dietrich Paulus, John K. Tsotsos
This leads to a viewpoint that provides a more accurate prediction to distinguish such an object from other objects better.
1 code implementation • 27 Sep 2021 • Michael Duhme, Raphael Memmesheimer, Dietrich Paulus
In this paper, we present Fusion-GCN, an approach for multimodal action recognition using Graph Convolutional Networks (GCNs).
Ranked #3 on Multimodal Activity Recognition on MMAct (F1-Score (Cross-Subject) metric)
1 code implementation • 26 Dec 2020 • Raphael Memmesheimer, Simon Häring, Nick Theisen, Dietrich Paulus
One-shot action recognition allows the recognition of human-performed actions with only a single training example.
Ranked #2 on One-Shot 3D Action Recognition on NTU RGB+D 120
1 code implementation • 23 Apr 2020 • Raphael Memmesheimer, Nick Theisen, Dietrich Paulus
Further, we show that our approach generalizes well in experiments on the UTD-MHAD dataset for inertial, skeleton and fused data and the Simitate dataset for motion capturing data.
Ranked #3 on One-Shot 3D Action Recognition on NTU RGB+D 120
2 code implementations • 13 Mar 2020 • Raphael Memmesheimer, Nick Theisen, Dietrich Paulus
We present a simple, yet effective and flexible method for action recognition supporting multiple sensor modalities.
Ranked #2 on Multimodal Activity Recognition on UTD-MHAD
1 code implementation • 25 Jun 2019 • Pascal Schneider, Raphael Memmesheimer, Ivanna Kramer, Dietrich Paulus
This paper presents a method for gesture recognition in RGB videos using OpenPose to extract the pose of a person and Dynamic Time Warping (DTW) in conjunction with One-Nearest-Neighbor (1NN) for time-series classification.
3 code implementations • 15 May 2019 • Raphael Memmesheimer, Ivanna Mykhalchyshyna, Viktor Seib, Dietrich Paulus
We present Simitate --- a hybrid benchmarking suite targeting the evaluation of approaches for imitation learning.
1 code implementation • 14 May 2019 • Raphael Memmesheimer, Isabelle Kuhlmann, Mark Mints, Patrik Schmidt, Christian Korbach, Ida Germann, Dietrich Paulus
We present Scratchy---a modular, lightweight robot built for low budget competition attendances.
Robotics
no code implementations • 30 Jul 2018 • Raphael Memmesheimer, Ivanna Mykhalchyshyna, Viktor Seib, Nick Theisen, Dietrich Paulus
We analyze a set of spatial constraints on human pose data extracted using convolutional pose machines and object informations extracted from 2D image sequences.
75 code implementations • 21 Mar 2017 • Nicolai Wojke, Alex Bewley, Dietrich Paulus
Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms.
Ranked #52 on Video Instance Segmentation on YouTube-VIS validation
Large-Scale Person Re-Identification Multiple Object Tracking +1