no code implementations • 27 Feb 2024 • Marsil Zakour, Partha Pratim Nath, Ludwig Lohmer, Emre Faik Gökçe, Martin Piccolrovazzi, Constantin Patsch, Yuankai Wu, Rahul Chaudhari, Eckehard Steinbach
However, existing datasets for 4D HOI (3D HOI over time) are limited to one subject inter- acting with one object only.
no code implementations • 27 Feb 2024 • H. Burak Dogaroglu, A. Burakhan Koyuncu, Atanas Boev, Elena Alshina, Eckehard Steinbach
As learned image codecs (LICs) become more prevalent, their low coding efficiency for out-of-distribution data becomes a bottleneck for some applications.
no code implementations • 14 Dec 2023 • Sabri Mustafa Kahya, Muhammet Sami Yavuz, Eckehard Steinbach
We propose HAROOD as a short-range FMCW radar-based human activity classifier and out-of-distribution (OOD) detector.
1 code implementation • 9 Oct 2023 • Michael G. Adam, Sebastian Eger, Martin Piccolrovazzi, Maged Iskandar, Joern Vogel, Alexander Dietrich, Seongjien Bien, Jon Skerlj, Abdeldjallil Naceri, Eckehard Steinbach, Alin Albu-Schaeffer, Sami Haddadin, Wolfram Burgard
As labor shortage increases in the health sector, the demand for assistive robotics grows.
no code implementations • 24 Jul 2023 • Sabri Mustafa Kahya, Muhammet Sami Yavuz, Eckehard Steinbach
HOOD solves the human presence and OOD detection problems simultaneously in a single pipeline.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 25 Jun 2023 • A. Burakhan Koyuncu, Panqi Jia, Atanas Boev, Elena Alshina, Eckehard Steinbach
Entropy estimation is essential for the performance of learned image compression.
1 code implementation • 17 Mar 2023 • Furkan Kaynar, Sudarshan Rajagopalan, Shaobo Zhou, Eckehard Steinbach
We receive grasp area demonstrations for a new task via interactive segmentation, and learn from these few demonstrations to estimate the required grasp area on an unseen scene for the given task.
no code implementations • 10 Mar 2023 • Sabri Mustafa Kahya, Muhammet Sami Yavuz, Eckehard Steinbach
The simple idea is called respiration detector (RESPD) and eases the OOD detection, especially for human sitting and standing classes.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 27 Feb 2023 • Sabri Mustafa Kahya, Muhammet Sami Yavuz, Eckehard Steinbach
Out-of-distribution (OOD) detection recently has drawn attention due to its critical role in the safe deployment of modern neural network architectures in real-world applications.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
1 code implementation • 8 Jul 2022 • Michael G. Adam, Martin Piccolrovazzi, Sebastian Eger, Eckehard Steinbach
The most popular evaluation metric for object detection in 2D images is Intersection over Union (IoU).
no code implementations • 13 May 2022 • Kristian Fischer, Markus Hofbauer, Christopher Kuhn, Eckehard Steinbach, André Kaup
To mitigate this problem, we propose an evaluation method based on pseudo ground-truth data from the field of semantic segmentation to the evaluation of video coding for machines.
no code implementations • 4 Mar 2022 • A. Burakhan Koyuncu, Han Gao, Atanas Boev, Georgii Gaikov, Elena Alshina, Eckehard Steinbach
Entropy modeling is a key component for high-performance image compression algorithms.
1 code implementation • 7 Oct 2018 • Kai Cui, Zhi Jin, Eckehard Steinbach
Color demosaicking (CDM) is a critical first step for the acquisition of high-quality RGB images with single chip cameras.
no code implementations • 5 Apr 2018 • Dmytro Bobkov, Sili Chen, Ruiqing Jian, Muhammad Iqbal, Eckehard Steinbach
To address this issue, we propose a point pair descriptor that is robust to noise and occlusion and achieves high retrieval accuracy.
no code implementations • 21 Dec 2015 • Haitian Zheng, Lu Fang, Mengqi Ji, Matti Strese, Yigitcan Ozer, Eckehard Steinbach
When a user scratches a hand-held rigid tool across an object surface, an acceleration signal can be captured, which carries relevant information about the surface.
1 code implementation • 5 Oct 2015 • Christoph Bachhuber, Eckehard Steinbach
To judge the quality of the video transmission in such a system, it is important to be able to precisely measure the end-to-end (E2E) delay of the transmitted video.
Multimedia
no code implementations • 27 Jun 2015 • Jianshu Chao, Eckehard Steinbach
As a result, the bitrate of the side information related to keypoint encoding is significantly reduced.