Graham W Taylor

is this you? claim profile

∙ 0 followers
University of Guelph

Associate Professor School of Engineering at University of Guelph and Vector Institute

SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation

In this paper we introduce a Transformer-based approach to video object ...
01/21/2021 ∙ by Brendan Duke, et al. ∙ 0 ∙ share

read it
Building LEGO Using Deep Generative Models of Graphs

Generative models are now used to create a variety of high-quality digit...
12/21/2020 ∙ by Rylee Thompson, et al. ∙ 0 ∙ share

read it
Evaluating Curriculum Learning Strategies in Neural Combinatorial Optimization

Neural combinatorial optimization (NCO) aims at designing problem-indepe...
11/12/2020 ∙ by Michal Lisicki, et al. ∙ 0 ∙ share

read it
Identifying and interpreting tuning dimensions in deep networks

In neuroscience, a tuning dimension is a stimulus attribute that account...
11/05/2020 ∙ by Nolan S. Dey, et al. ∙ 26 ∙ share

read it
Instance Selection for GANs

Recent advances in Generative Adversarial Networks (GANs) have led to th...
07/30/2020 ∙ by Terrance DeVries, et al. ∙ 0 ∙ share

read it
Generative Graph Perturbations for Scene Graph Prediction

Inferring objects and their relationships from an image is useful in man...
07/11/2020 ∙ by Boris Knyazev, et al. ∙ 0 ∙ share

read it
Enabling Continual Learning with Differentiable Hebbian Plasticity

Continual learning is the problem of sequentially learning new tasks or ...
06/30/2020 ∙ by Vithursan Thangarasa, et al. ∙ 0 ∙ share

read it
Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation

Scene graph generation (SGG) aims to predict graph-structured descriptio...
05/17/2020 ∙ by Boris Knyazev, et al. ∙ 0 ∙ share

read it
Sample-Efficient Model-based Actor-Critic for an Interactive Dialogue Task

Human-computer interactive systems that rely on machine learning are bec...
04/28/2020 ∙ by Katya Kudashkina, et al. ∙ 0 ∙ share

read it
ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis

We consider the problem of distance metric learning (DML), where the tas...
04/02/2020 ∙ by Eu Wern Teh, et al. ∙ 0 ∙ share

read it
Learning with less data via Weakly Labeled Patch Classification in Digital Pathology

In Digital Pathology (DP), labeled data is generally very scarce due to ...
11/27/2019 ∙ by Eu Wern Teh, et al. ∙ 0 ∙ share

read it
Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking

Deep neural networks require collecting and annotating large amounts of ...
10/28/2019 ∙ by Alaaeldin El-Nouby, et al. ∙ 12 ∙ share

read it
A Nonparametric Bayesian Model for Sparse Temporal Multigraphs

As the availability and importance of temporal interaction data–such as ...
10/11/2019 ∙ by Elahe Ghalebi, et al. ∙ 0 ∙ share

read it
Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions

Graphs evolving over time are a natural way to represent data in many do...
09/23/2019 ∙ by Boris Knyazev, et al. ∙ 3 ∙ share

read it
Image Classification with Hierarchical Multigraph Networks

Graph Convolutional Networks (GCNs) are a class of general models that c...
07/21/2019 ∙ by Boris Knyazev, et al. ∙ 4 ∙ share

read it
On the Evaluation of Conditional GANs

Conditional Generative Adversarial Networks (cGANs) are finding increasi...
07/11/2019 ∙ by Terrance DeVries, et al. ∙ 8 ∙ share

read it
Understanding attention in graph neural networks

We aim to better understand attention over nodes in graph neural network...
05/08/2019 ∙ by Boris Knyazev, et al. ∙ 0 ∙ share

read it
Batch Normalization is a Cause of Adversarial Vulnerability

Batch normalization (batch norm) is often used in an attempt to stabiliz...
05/06/2019 ∙ by Angus Galloway, et al. ∙ 0 ∙ share

read it
Similarity Learning Networks for Animal Individual Re-Identification - Beyond the Capabilities of a Human Observer

The ability of a researcher to re-identify (re-ID) an animal individual ...
02/21/2019 ∙ by Stefan Schneider, et al. ∙ 0 ∙ share

read it
SISC: End-to-end Interpretable Discovery Radiomics-Driven Lung Cancer Prediction via Stacked Interpretable Sequencing Cells

Objective: Lung cancer is the leading cause of cancer-related death worl...
01/15/2019 ∙ by Vignesh Sankar, et al. ∙ 2 ∙ share

read it
Adversarial Examples as an Input-Fault Tolerance Problem

We analyze the adversarial examples problem in terms of a model's fault ...
11/30/2018 ∙ by Angus Galloway, et al. ∙ 0 ∙ share

read it
Keep Drawing It: Iterative language-based image generation and editing

Conditional text-to-image generation approaches commonly focus on genera...
11/24/2018 ∙ by Alaaeldin El-Nouby, et al. ∙ 0 ∙ share

read it
Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules

Spectral Graph Convolutional Networks (GCNs) are a generalization of con...
11/23/2018 ∙ by Boris Knyazev, et al. ∙ 0 ∙ share

read it
Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data

The ability of a researcher to re-identify (re-ID) an individual animal ...
11/19/2018 ∙ by Stefan Schneider, et al. ∙ 0 ∙ share

read it
Self-Paced Learning with Adaptive Deep Visual Embeddings

Selecting the most appropriate data examples to present a deep neural ne...
07/24/2018 ∙ by Vithursan Thangarasa, et al. ∙ 0 ∙ share

read it
Stochastic Layer-Wise Precision in Deep Neural Networks

Low precision weights, activations, and gradients have been proposed as ...
07/03/2018 ∙ by Griffin Lacey, et al. ∙ 0 ∙ share

read it
Leveraging Uncertainty Estimates for Predicting Segmentation Quality

The use of deep learning for medical imaging has seen tremendous growth ...
07/02/2018 ∙ by Terrance DeVries, et al. ∙ 4 ∙ share

read it
Adversarial Training Versus Weight Decay

Performance-critical machine learning models should be robust to input p...
04/10/2018 ∙ by Angus Galloway, et al. ∙ 0 ∙ share

read it
Deep Learning Object Detection Methods for Ecological Camera Trap Data

Deep learning methods for computer vision tasks show promise for automat...
03/28/2018 ∙ by Stefan Schneider, et al. ∙ 0 ∙ share

read it
Generalized Hadamard-Product Fusion Operators for Visual Question Answering

We propose a generalized class of multimodal fusion operators for the ta...
03/26/2018 ∙ by Brendan Duke, et al. ∙ 0 ∙ share

read it
Real-Time End-to-End Action Detection with Two-Stream Networks

Two-stream networks have been very successful for solving the problem of...
02/23/2018 ∙ by Alaaeldin El-Nouby, et al. ∙ 0 ∙ share

read it
Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points

We propose a method for human activity recognition from RGB data which d...
02/22/2018 ∙ by Fabien Baradel, et al. ∙ 0 ∙ share

read it
Learning Confidence for Out-of-Distribution Detection in Neural Networks

Modern neural networks are very powerful predictive models, but they are...
02/13/2018 ∙ by Terrance DeVries, et al. ∙ 0 ∙ share

read it
Predicting Adversarial Examples with High Confidence

It has been suggested that adversarial examples cause deep learning mode...
02/13/2018 ∙ by Angus Galloway, et al. ∙ 0 ∙ share

read it
Attacking Binarized Neural Networks

Neural networks with low-precision weights and activations offer compell...
11/01/2017 ∙ by Angus Galloway, et al. ∙ 0 ∙ share

read it
Discovery Radiomics with CLEAR-DR: Interpretable Computer Aided Diagnosis of Diabetic Retinopathy

Objective: Radiomics-driven Computer Aided Diagnosis (CAD) has shown con...
10/29/2017 ∙ by Devinder Kumar, et al. ∙ 0 ∙ share

read it
Opening the Black Box of Financial AI with CLEAR-Trade: A CLass-Enhanced Attentive Response Approach for Explaining and Visualizing Deep Learning-Driven Stock Market Prediction

Deep learning has been shown to outperform traditional machine learning ...
09/05/2017 ∙ by Devinder Kumar, et al. ∙ 0 ∙ share

read it
Structure Optimization for Deep Multimodal Fusion Networks using Graph-Induced Kernels

A popular testbed for deep learning has been multimodal recognition of h...
07/03/2017 ∙ by Dhanesh Ramachandram, et al. ∙ 0 ∙ share

read it
Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks

In this work, we propose CLass-Enhanced Attentive Response (CLEAR): an a...
04/13/2017 ∙ by Devinder Kumar, et al. ∙ 0 ∙ share

read it
Dataset Augmentation in Feature Space

Dataset augmentation, the practice of applying a wide array of domain-sp...
02/17/2017 ∙ by Terrance DeVries, et al. ∙ 0 ∙ share

read it
An Integrated Simulator and Dataset that Combines Grasping and Vision for Deep Learning

Deep learning is an established framework for learning hierarchical data...
02/07/2017 ∙ by Matthew Veres, et al. ∙ 0 ∙ share

read it
Modeling Grasp Motor Imagery through Deep Conditional Generative Models

Grasping is a complex process involving knowledge of the object, the sur...
01/11/2017 ∙ by Matthew Veres, et al. ∙ 0 ∙ share

read it
Learning a metric for class-conditional KNN

Naive Bayes Nearest Neighbour (NBNN) is a simple and effective framework...
07/11/2016 ∙ by Daniel Jiwoong Im, et al. ∙ 0 ∙ share

read it
Deep Learning on FPGAs: Past, Present, and Future

The rapid growth of data size and accessibility in recent years has inst...
02/13/2016 ∙ by Griffin Lacey, et al. ∙ 0 ∙ share

read it
ModDrop: adaptive multi-modal gesture recognition

We present a method for gesture detection and localisation based on mult...
12/31/2014 ∙ by Natalia Neverova, et al. ∙ 0 ∙ share

read it
Neural Network Regularization via Robust Weight Factorization

Regularization is essential when training large neural networks. As deep...
12/20/2014 ∙ by Jan Rudy, et al. ∙ 0 ∙ share

read it
Scoring and Classifying with Gated Auto-encoders

Auto-encoders are perhaps the best-known non-probabilistic methods for r...
12/20/2014 ∙ by Daniel Jiwoong Im, et al. ∙ 0 ∙ share

read it
"Mental Rotation" by Optimizing Transforming Distance

The human visual system is able to recognize objects despite transformat...
06/11/2014 ∙ by Weiguang Ding, et al. ∙ 0 ∙ share

read it
Learning Human Pose Estimation Features with Convolutional Networks

This paper introduces a new architecture for human pose estimation using...
12/27/2013 ∙ by Arjun Jain, et al. ∙ 0 ∙ share

read it
Products of Hidden Markov Models: It Takes N>1 to Tango

Products of Hidden Markov Models(PoHMMs) are an interesting class of gen...
05/09/2012 ∙ by Graham W Taylor, et al. ∙ 0 ∙ share

read it

Graham W Taylor

Featured Co-authors