34 citations · 35 across the 2 of their papers we have counts for
3 papers
cs.CV2026
Action Forcing: Training World Models on Unsupervised Video by Recovering Underlying Egomotion Bases
Ashish Sundar, Tiankuo Hou, Zhong Fan +2
Synchronised action annotations are needed to train controllable world models and these datasets remain elusive. Existing approaches make use of instrumented platforms with calibra…
physics.med-ph2023★ 1 cited
ECG Feature Importance Rankings: Cardiologists vs. Algorithms
Temesgen Mehari, Ashish Sundar, Alen Bosnjakovic +7
Feature importance methods promise to provide a ranking of features according to importance for a given classification task. A wide range of methods exist but their rankings often…
eess.SP2021★ 34 cited
Robustness of convolutional neural networks to physiological ECG noise
J. Venton, P. M. Harris, A. Sundar +2
The electrocardiogram (ECG) is one of the most widespread diagnostic tools in healthcare and supports the diagnosis of cardiovascular disorders. Deep learning methods are a success…