no code implementations • 27 Nov 2023 • Zeyun Zhong, Chengzhi Wu, Manuel Martin, Michael Voit, Juergen Gall, Jürgen Beyerer
However, the majority of existing action anticipation models adhere to a deterministic approach, neglecting to account for future uncertainties.
1 code implementation • 18 Nov 2023 • Nils Friederich, Andreas Specker, Jürgen Beyerer
In this work, we explore object detection methods to address the fence inspection task and localize various types of damages.
no code implementations • 29 Sep 2023 • Zeyun Zhong, Manuel Martin, Michael Voit, Juergen Gall, Jürgen Beyerer
The ability to anticipate possible future human actions is essential for a wide range of applications, including autonomous driving and human-robot interaction.
no code implementations • 29 Apr 2023 • Ankush Meshram, Markus Karch, Christian Haas, Jürgen Beyerer
It successfully detects and reports the anomalies triggered by a network attack in a miniaturized PROFINET-based industrial system, executed through valid network protocol exchanges and resulting in invalid PROFINET operation transition for the device.
no code implementations • 17 Apr 2023 • Chengzhi Wu, Junwei Zheng, Julius Pfrommer, Jürgen Beyerer
Modeling a 3D volumetric shape as an assembly of decomposed shape parts is much more challenging, but semantically more valuable than direct reconstruction from a full shape representation.
1 code implementation • CVPR 2023 • Tobias Kalb, Jürgen Beyerer
Deep neural networks for scene perception in automated vehicles achieve excellent results for the domains they were trained on.
1 code implementation • CVPR 2023 • Chengzhi Wu, Junwei Zheng, Julius Pfrommer, Jürgen Beyerer
Point cloud sampling is a less explored research topic for this data representation.
Ranked #31 on 3D Point Cloud Classification on ModelNet40
no code implementations • 21 Feb 2023 • Tobias Kalb, Niket Ahuja, Jingxing Zhou, Jürgen Beyerer
Specifically, we compare the well-researched CNNs to recently proposed Transformers and Hybrid architectures, as well as the impact of the choice of novel normalization layers and different decoder heads.
no code implementations • 12 Jan 2023 • Chengzhi Wu, Xuelei Bi, Julius Pfrommer, Alexander Cebulla, Simon Mangold, Jürgen Beyerer
On robotics computer vision tasks, generating and annotating large amounts of data from real-world for the use of deep learning-based approaches is often difficult or even impossible.
no code implementations • 11 Jan 2023 • Chengzhi Wu, Linxi Qiu, Kanran Zhou, Julius Pfrommer, Jürgen Beyerer
Our work is a sub-task in the framework of a remanufacturing project, in which small electric motors are used as fundamental objects.
no code implementations • 11 Jan 2023 • Chengzhi Wu, Kanran Zhou, Jan-Philipp Kaiser, Norbert Mitschke, Jan-Felix Klein, Julius Pfrommer, Jürgen Beyerer, Gisela Lanza, Michael Heizmann, Kai Furmans
To enable automatic disassembly of different product types with uncertain conditions and degrees of wear in remanufacturing, agile production systems that can adapt dynamically to changing requirements are needed.
no code implementations • 11 Jan 2023 • Chengzhi Wu, Julius Pfrommer, Jürgen Beyerer, Kangning Li, Boris Neubert
We present an improved approach for 3D object detection in point cloud data based on the Frustum PointNet (F-PointNet).
no code implementations • 11 Jan 2023 • Chengzhi Wu, Julius Pfrommer, Mingyuan Zhou, Jürgen Beyerer
We propose a combined generative and contrastive neural architecture for learning latent representations of 3D volumetric shapes.
1 code implementation • 23 Oct 2022 • Zeyun Zhong, David Schneider, Michael Voit, Rainer Stiefelhagen, Jürgen Beyerer
Although human action anticipation is a task which is inherently multi-modal, state-of-the-art methods on well known action anticipation datasets leverage this data by applying ensemble methods and averaging scores of unimodal anticipation networks.
Ranked #2 on Action Anticipation on EPIC-KITCHENS-100
1 code implementation • 20 Sep 2022 • Tobias Kalb, Björn Mauthe, Jürgen Beyerer
Continual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains.
no code implementations • 16 Sep 2022 • Tobias Kalb, Masoud Roschani, Miriam Ruf, Jürgen Beyerer
Therefore, the goal of our work is to evaluate and adapt established solutions for continual object recognition to the task of semantic segmentation and to provide baseline methods and evaluation protocols for the task of continual semantic segmentation.
Class-Incremental Semantic Segmentation Continual Semantic Segmentation +6
1 code implementation • 16 Sep 2022 • Tobias Kalb, Jürgen Beyerer
Therefore, in a set of experiments and representational analyses, we demonstrate that the semantic shift of the background class and a bias towards new classes are the major causes of forgetting in CiSS.
Class-Incremental Semantic Segmentation Incremental Learning +2
1 code implementation • 6 Sep 2022 • Andreas Specker, Mickael Cormier, Jürgen Beyerer
It is based on four well-known person attribute recognition datasets: PA100K, PETA, RAPv2, and Market1501.
1 code implementation • 26 May 2022 • Hannah Schieber, Fabian Duerr, Torsten Schoen, Jürgen Beyerer
A novel Pyramid Fusion Backbone fuses these feature maps at different scales and combines the multimodal features in a feature pyramid to compute valuable multimodal, multi-scale features.
no code implementations • 3 May 2022 • Ronny Hug, Stefan Becker, Wolfgang Hübner, Michael Arens, Jürgen Beyerer
Probabilistic models for sequential data are the basis for a variety of applications concerned with processing timely ordered information.
no code implementations • 10 Apr 2022 • Jan Burke, Alexey Pak, Sebastian Höfer, Mathias Ziebarth, Masoud Roschani, Jürgen Beyerer
Deflectometry as a technical approach to assessing reflective surfaces has now existed for almost 40 years.
no code implementations • 15 Jun 2021 • Boitumelo Ruf, Jonas Mohrs, Martin Weinmann, Stefan Hinz, Jürgen Beyerer
In this, we propose an optimization of the algorithm for embedded CUDA GPUs, by using massively parallel computing, as well as using the NEON intrinsics to optimize the algorithm for vectorized SIMD processing on embedded ARM CPUs.
no code implementations • 10 Apr 2021 • Mickael Cormier, Houraalsadat Mortazavi Moshkenan, Franz Lörch, Jürgen Metzler, Jürgen Beyerer
Our goal is to transfer the motion of real people from a source video to a target video with realistic results.
1 code implementation • 16 Jul 2019 • Thomas Golda, Tobias Kalb, Arne Schumann, Jürgen Beyerer
In order to overcome the transfer gap of JTA originating from a low pose variety and less dense crowds, an extension dataset is created to ease the use for real-world applications.
Ranked #14 on Multi-Person Pose Estimation on CrowdPose
1 code implementation • 8 Jun 2018 • Krassimir Valev, Arne Schumann, Lars Sommer, Jürgen Beyerer
Fine-grained vehicle classification is the task of classifying make, model, and year of a vehicle.
1 code implementation • 30 Oct 2017 • Andras Tüzkö, Christian Herrmann, Daniel Manger, Jürgen Beyerer
Given a query sample in shape of a logo image, the task is to find all further occurrences of this logo in a set of images or videos.
no code implementations • 8 Aug 2017 • Manuel Günther, Peiyun Hu, Christian Herrmann, Chi Ho Chan, Min Jiang, Shufan Yang, Akshay Raj Dhamija, Deva Ramanan, Jürgen Beyerer, Josef Kittler, Mohamad Al Jazaery, Mohammad Iqbal Nouyed, Guodong Guo, Cezary Stankiewicz, Terrance E. Boult
Face detection and recognition benchmarks have shifted toward more difficult environments.
no code implementations • 14 Sep 2014 • Jonathan Balzer, Daniel Acevedo-Feliz, Stefano Soatto, Sebastian Höfer, Markus Hadwiger, Jürgen Beyerer
We introduce a method based on the deflectometry principle for the reconstruction of specular objects exhibiting significant size and geometric complexity.