101 citations · 245 across the 16 of their papers we have counts for
16 papers
MMASD: A Multimodal Dataset for Autism Intervention Analysis
Jicheng Li, Vuthea Chheang, Pinar Kullu +5
Autism spectrum disorder (ASD) is a developmental disorder characterized by significant social communication impairments and difficulties perceiving and presenting communication cu…
Social Visual Behavior Analytics for Autism Therapy of Children Based on Automated Mutual Gaze Detection
Zhang Guo, Vuthea Chheang, Jicheng Li +3
Social visual behavior, as a type of non-verbal communication, plays a central role in studying social cognitive processes in interactive and complex settings of autism therapy int…
A Black-Box Attack on Optical Character Recognition Systems
Samet Bayram, Kenneth Barner
Adversarial machine learning is an emerging area showing the vulnerability of deep learning models. Exploring attack methods to challenge state of the art artificial intelligence (…
A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization
Xinjie Lan, Kenneth Barner
Recently, Mutual Information (MI) has attracted attention in bounding the generalization error of Deep Neural Networks (DNNs). However, it is intractable to accurately estimate the…
A Probabilistic Representation of Deep Learning for Improving The Information Theoretic Interpretability
Xinjie Lan, Kenneth E. Barner
In this paper, we propose a probabilistic representation of MultiLayer Perceptrons (MLPs) to improve the information-theoretic interpretability. Above all, we demonstrate that the…
PAC-Bayesian Generalization Bounds for MultiLayer Perceptrons
Xinjie Lan, Xin Guo, Kenneth E. Barner
We study PAC-Bayesian generalization bounds for Multilayer Perceptrons (MLPs) with the cross entropy loss. Above all, we introduce probabilistic explanations for MLPs in two aspect…
Audio-video Emotion Recognition in the Wild using Deep Hybrid Networks
Xin Guo, Luisa F. Polanía, Kenneth E. Barner
This paper presents an audiovisual-based emotion recognition hybrid network. While most of the previous work focuses either on using deep models or hand-engineered features extract…
Explicitly Bayesian Regularizations in Deep Learning
Xinjie Lan, Kenneth E. Barner
Generalization is essential for deep learning. In contrast to previous works claiming that Deep Neural Networks (DNNs) have an implicit regularization implemented by the stochastic…
Automatic Group Cohesiveness Detection With Multi-modal Features
Bin Zhu, Xin Guo, Kenneth Barner +1
Group cohesiveness is a compelling and often studied composition in group dynamics and group performance. The enormous number of web images of groups of people can be used to devel…
Graph Neural Networks for Image Understanding Based on Multiple Cues: Group Emotion Recognition and Event Recognition as Use Cases
Xin Guo, Luisa F. Polania, Bin Zhu +2
A graph neural network (GNN) for image understanding based on multiple cues is proposed in this paper. Compared to traditional feature and decision fusion approaches that neglect t…
A Probabilistic Representation of Deep Learning
Xinjie Lan, Kenneth E. Barner
In this work, we introduce a novel probabilistic representation of deep learning, which provides an explicit explanation for the Deep Neural Networks (DNNs) in three aspects: (i) n…
Bayesian Convolutional Neural Networks for Compressed Sensing Restoration
Xinjie Lan, Xin Guo, Kenneth E. Barner
Deep Neural Networks (DNNs) have aroused great attention in Compressed Sensing (CS) restoration. However, the working mechanism of DNNs is not explainable, thereby it is unclear th…
Smile detection in the wild based on transfer learning
Xin Guo, Luisa F. Polanía, Kenneth E. Barner
Smile detection from unconstrained facial images is a specialized and challenging problem. As one of the most informative expressions, smiles convey basic underlying emotions, such…
Exploiting Restricted Boltzmann Machines and Deep Belief Networks in Compressed Sensing
Luisa F. Polania, Kenneth E. Barner
This paper proposes a CS scheme that exploits the representational power of restricted Boltzmann machines and deep learning architectures to model the prior distribution of the spa…
Exploiting Prior Knowledge in Compressed Sensing Wireless ECG Systems
Luisa F. Polania, Rafael E. Carrillo, Manuel Blanco-Velasco +1
Recent results in telecardiology show that compressed sensing (CS) is a promising tool to lower energy consumption in wireless body area networks for electrocardiogram (ECG) monito…
Lorentzian Iterative Hard Thresholding: Robust Compressed Sensing with Prior Information
Rafael E. Carrillo, Kenneth E. Barner
Commonly employed reconstruction algorithms in compressed sensing (CS) use the norm as the metric for the residual error. However, it is well-known that least squares (LS) ba…