9 citations · 19 across the 11 of their papers we have counts for
12 papers
EGiME: Entropy-Guided Model Evaluation in Few-Shot Learning
Dequan Jin, Tao Li, Lifeng Xing +2
The feature-extraction quality of pre-trained models sets the ceiling of downstream transfer learning, yet few-shot model selection remains difficult: supervised evaluation on scar…
VAMP-Diff: VampPrior Latent Diffusion for Photoplethysmography Modeling
Fatemeh Ghasemi Balouei, Nathan Willemsen, Mahesh Banavar +1
Photoplethysmography (PPG) has become a ubiquitous physiological signal; however, current generative models still struggle to preserve realistic waveform morphology and learn a lat…
Nested Inheritance Dynamics
Bahman Moraffah
The idea of the inheritance of biological processes, such as the developmental process or the life cycle of an organism, has been discussed in the biology literature, but formal ma…
Bayesian Nonparametrics: An Alternative to Deep Learning
Bahman Moraffah
Bayesian nonparametric models offer a flexible and powerful framework for statistical model selection, enabling the adaptation of model complexity to the intricacies of diverse dat…
A Complete Recipe for Bayesian Knowledge Transfer: Object Tracking
Bahman Moraffah, Antonia Papandreou-Suppappola
The problem of sequentially transferring from a source object track and a model to another Bayesian filter has become ubiquitous. Due to the lack of a structural model that can cap…
Bayesian Nonparametric View to Spawning
Bahman Moraffah
In tracking multiple objects, it is often assumed that each observation (measurement) is originated from one and only one object. However, we may encounter a situation that each me…
Bayesian Nonparametric Modelling for Model-Free Reinforcement Learning in LTE-LAA and Wi-Fi Coexistence
Po-Kan Shih, Bahman Moraffah
With the arrival of next generation wireless communication, a growing number of new applications like internet of things, autonomous driving systems, and drone are crowding the unl…
Use of Bayesian Nonparametric methods for Estimating the Measurements in High Clutter
Bahman Moraffah, Christ Richmond, Raha Moraffah +1
Robust tracking of a target in a clutter environment is an important and challenging task. In recent years, the nearest neighbor methods and probabilistic data association filters…
Causal Adversarial Network for Learning Conditional and Interventional Distributions
Raha Moraffah, Bahman Moraffah, Mansooreh Karami +2
We propose a generative Causal Adversarial Network (CAN) for learning and sampling from conditional and interventional distributions. In contrast to the existing CausalGAN which re…
Bayesian nonparametric modeling for predicting dynamic dependencies in multiple object tracking
Bahman Moraffah, Antonia Papndreou-Suppopola
Some challenging problems in tracking multiple objects include the time-dependent cardinality, unordered measurements and object parameter labeling. In this paper, we employ Bayesi…
Inference for multiple object tracking: A Bayesian nonparametric approach
Bahman Moraffah
In recent years, multi object tracking (MOT) problem has drawn attention to it and has been studied in various research areas. However, some of the challenging problems including t…
Privacy-guaranteed Two-Agent Interactions Using Information-Theoretic Mechanisms
Bahman Moraffah, Lalitha Sankar
This paper introduces a multi-round interaction problem with privacy constraints between two agents that observe correlated data. The agents alternately share data with one another…