Brian Davis — accepted AI-conference papers

2024

Beyond Binary: Towards Embracing Complexities in Cyberbullying Detection and Intervention - a Position Paper

Kanishk Verma, Kolawole John Adebayo, Joachim Wagner, Megan Reynolds, Rebecca Umbach, Tijana Milosevic +1

COLING 2024main

In the digital age, cyberbullying (CB) poses a significant concern, impacting individuals as early as primary school and leading to severe or lasting consequences, including an increased risk of self-harm. CB incidents, are not limited to bullies and victims, but include bystanders with various role…

Cited by 4 Source ↗PDF ↗Scholar ↗

2022

Optimal Inverted Landing in a Small Aerial Robot with Varied Approach Velocities and Landing Gear Designs

Bryan Habas, Bader AlAttar, Brian Davis, Jack W. Langelaan, Bo Cheng

ICRA 2022poster

Inverted landing is a challenging feat to perform in aerial robots, especially without external positioning. However, it is routinely performed by biological fliers such as bees, flies, and bats. Our previous observations of landing behaviors in flies suggest an open-loop causal relationship between…

Cited by 9 Source ↗Scholar ↗

2020

On Network Science and Mutual Information for Explaining Deep Neural Networks

Brian Davis, Umang Bhatt, Kartikeya Bhardwaj, Radu Marculescu, José M. F. Moura

ICASSP 2020accepted

In this paper, we present a new approach to interpret deep learning models. By coupling mutual information with network science, we explore how information flows through feedforward networks. We show that efficiently approximating mutual information allows us to create an information measure that qu…

Cited by 0 Source ↗Scholar ↗

2018

Start, Follow, Read: End-to-End Full-Page Handwriting Recognition

Curtis Wigington, Chris Tensmeyer, Brian Davis, William Barrett, Brian Price, Scott Cohen

ECCV 2018poster

Despite decades of research, offline handwriting recognition (HWR) of degraded historical documents remains a challenging problem, which if solved could greatly improve the searchability of online cultural heritage archives. HWR models are often limited by the accuracy of the preceding steps of text…

Cited by 148 Source ↗PDF ↗code ↗Scholar ↗