Search Results for author: Umar Asif

Found 7 papers, 3 papers with code

Towards Automated and Marker-less Parkinson Disease Assessment: Predicting UPDRS Scores using Sit-stand videos

no code implementations10 Apr 2021 Deval Mehta, Umar Asif, Tian Hao, Erhan Bilal, Stefan von Cavallar, Stefan Harrer, Jeffrey Rogers

For BRADY we find F1-scores of 0. 75 using our framework compared to 0. 50 for the video based rater clinicians, while for PIGD we find 0. 78 for the framework and 0. 45 for the video based rater clinicians.

DeepActsNet: Spatial and Motion features from Face, Hands, and Body Combined with Convolutional and Graph Networks for Improved Action Recognition

no code implementations21 Sep 2020 Umar Asif, Deval Mehta, Stefan von Cavallar, Jianbin Tang, Stefan Harrer

Existing action recognition methods mainly focus on joint and bone information in human body skeleton data due to its robustness to complex backgrounds and dynamic characteristics of the environments.

Action Recognition

SSHFD: Single Shot Human Fall Detection with Occluded Joints Resilience

no code implementations2 Apr 2020 Umar Asif, Stefan von Cavallar, Jianbin Tang, Stefan Harrer

First, we present a human pose based fall representation which is invariant to appearance characteristics.

3D Pose Estimation

Ensemble Knowledge Distillation for Learning Improved and Efficient Networks

2 code implementations17 Sep 2019 Umar Asif, Jianbin Tang, Stefan Harrer

Ensemble models comprising of deep Convolutional Neural Networks (CNN) have shown significant improvements in model generalization but at the cost of large computation and memory requirements.

Ensemble Learning General Classification +2

SeizureNet: Multi-Spectral Deep Feature Learning for Seizure Type Classification

3 code implementations8 Mar 2019 Umar Asif, Subhrajit Roy, Jianbin Tang, Stefan Harrer

Automatic classification of epileptic seizure types in electroencephalograms (EEGs) data can enable more precise diagnosis and efficient management of the disease.

Classification EEG +6

Seizure Type Classification using EEG signals and Machine Learning: Setting a benchmark

1 code implementation4 Feb 2019 Subhrajit Roy, Umar Asif, Jianbin Tang, Stefan Harrer

On that note, in this paper, we explore the application of machine learning algorithms for multi-class seizure type classification.

BIG-bench Machine Learning Classification +5

Densely Supervised Grasp Detector (DSGD)

no code implementations1 Oct 2018 Umar Asif, Jianbin Tang, Stefan Harrer

At the pixel-level, DSGD uses a fully convolutional network and predicts a grasp and its confidence at every pixel.

Region Proposal Robotic Grasping

Cannot find the paper you are looking for? You can Submit a new open access paper.