User profiles for P. Faion

Patrick Faion

Master Student of Cognitive Science, University of Osnabrück
Verified email at uos.de
Cited by 61

Providing video annotations in multimedia containers for visualization and research

J Schöning, P Faion, G Heidemann… - 2017 IEEE Winter …, 2017 - ieeexplore.ieee.org
There is an ever increasing amount of video data sets which comprise additional metadata,
such as object labels, tagged events, or gaze data. Unfortunately, metadata are usually …

Semi-automatic ground truth annotation in videos: An interactive tool for polygon-based object annotation and segmentation

J Schöning, P Faion, G Heidemann - Proceedings of the 8th International …, 2015 - dl.acm.org
Knowledge extraction from video data is challenging due to its high complexity in both the
spatial and temporal domain. Ground truth is crucial for the evaluation and the adaptation of …

[PDF][PDF] Pixel-wise ground truth annotation in videos

J Schöning, P Faion, G Heidemann - ICPRAM, 2016 - academia.edu
In the last decades, a large diversity of automatic, semi-automatic and manual approaches for
video segmentation and knowledge extraction from video-data has been proposed. Due to …

Encoding and decoding dynamic sensory signals with recurrent neural networks: An application of conceptors to birdsongs

R Gast, P Faion, K Standvoss, A Suckro, B Lewis… - bioRxiv, 2017 - biorxiv.org
… In 8 η is the learning rate, m is the number of patterns stored in the RFC and P is a matrix
with a conceptor in each column. Thus, the change of γ is a function of the input to z, ie it is …

Eye tracking data in multimedia containers for instantaneous visualizations

J Schoning, P Faion, G Heidemann… - 2016 IEEE Second …, 2016 - ieeexplore.ieee.org
Nowadays, the amount of gaze data records of subjects associated with video sequences
increases daily. These eye tracking data are unfortunately stored in separate files in custom-…

Interactive feature growing for accurate object detection in megapixel images

J Schöning, P Faion, G Heidemann - … , The Netherlands, October 8-10 and …, 2016 - Springer
Automatic object detection in megapixel images is quite inaccurate and a time and memory
expensive task, even with feature detectors and descriptors like SIFT, SURF, ORB, and KAZE…

[PDF][PDF] Semi-automatic ground truth annotation in videos

J Schöning, P Faion… - … on Knowledge Capture …, 2015 - ikw.uni-osnabrueck.de
ABSTRACT Knowledge extraction from video data is challenging due to its high complexity
in both the spatial and temporal domain. Ground truth is crucial for the evaluation and the …

Structure from motion by artificial neural networks

J Schöning, T Behrens, P Faion, P Kheiri… - Image Analysis: 20th …, 2017 - Springer
Retrieving the 3D shape of an object from a collection of images or a video is currently
realized with multiple view geometry algorithms, most commonly Structure from Motion (SfM) …

Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms

H Xiao, K Rasul, R Vollgraf - arXiv preprint arXiv:1708.07747, 2017 - arxiv.org
… This paper introduced Fashion-MNIST, a fashion product images dataset intended to be
a dropin replacement of MNIST and whilst providing a more challenging alternative for …

Intelligent sensor-scheduling for multi-kinect-tracking

F Faion, S Friedberger, A Zea… - 2012 IEEE/RSJ …, 2012 - ieeexplore.ieee.org
This paper describes a method to intelligently schedule a network of multiple RGBD sensors
in a Bayesian object tracking scenario, with special focus on Microsoft KinectTM devices. …