69 citations · 208 across the 40 of their papers we have counts for
6 papers · 1 filter
Decision Level Fusion: An Event Driven Approach
Siddharth Roheda, Hamid Krim, Zhi-Quan Luo +1
This paper presents a technique that combines the occurrence of certain events, as observed by different sensors, in order to detect and classify objects. This technique explores t…
Cross-Modality Distillation: A case for Conditional Generative Adversarial Networks
Siddharth Roheda, Benjamin S. Riggan, Hamid Krim +1
In this paper, we propose to use a Conditional Generative Adversarial Network (CGAN) for distilling (i.e. transferring) knowledge from sensor data and enhancing low-resolution targ…
Analysis Dictionary Learning based Classification: Structure for Robustness
Wen Tang, Ashkan Panahi, Hamid Krim +1
A discriminative structured analysis dictionary is proposed for the classification task. A structure of the union of subspaces (UoS) is integrated into the conventional analysis di…
Structured Analysis Dictionary Learning for Image Classification
Wen Tang, Ashkan Panahi, Hamid Krim +1
We propose a computationally efficient and high-performance classification algorithm by incorporating class structural information in analysis dictionary learning. To achieve more…
Demystifying Deep Learning: A Geometric Approach to Iterative Projections
Ashkan Panahi, Hamid Krim, Liyi Dai
Parametric approaches to Learning, such as deep learning (DL), are highly popular in nonlinear regression, in spite of their extremely difficult training with their increasing comp…
Deep Dictionary Learning: A PARametric NETwork Approach
Shahin Mahdizadehaghdam, Ashkan Panahi, Hamid Krim +1
Deep dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method for learning a hierarchy of sy…