197 citations · 246 across the 14 of their papers we have counts for
16 papers
Bayesian uncertainty-weighted loss for improved generalisability on polyp segmentation task
Rebecca S. Stone, Pedro E. Chavarrias-Solano, Andrew J. Bulpitt +2
While several previous studies have devised methods for segmentation of polyps, most of these methods are not rigorously assessed on multi-center datasets. Variability due to appea…
A Horse with no Labels: Self-Supervised Horse Pose Estimation from Unlabelled Images and Synthetic Prior
Jose Sosa, David Hogg
Obtaining labelled data to train deep learning methods for estimating animal pose is challenging. Recently, synthetic data has been widely used for pose estimation tasks, but most…
3D shape reconstruction of semi-transparent worms
Thomas P. Ilett, Omer Yuval, Thomas Ranner +2
3D shape reconstruction typically requires identifying object features or textures in multiple images of a subject. This approach is not viable when the subject is semi-transparent…
Self-supervised 3D Human Pose Estimation from a Single Image
Jose Sosa, David Hogg
We propose a new self-supervised method for predicting 3D human body pose from a single image. The prediction network is trained from a dataset of unlabelled images depicting peopl…
Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network
Rebecca S Stone, Nishant Ravikumar, Andrew J Bulpitt +1
The fairness of a deep neural network is strongly affected by dataset bias and spurious correlations, both of which are usually present in modern feature-rich and complex visual da…
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
Yunfeng Diao, He Wang, Tianjia Shao +4
Human Activity Recognition (HAR) has been employed in a wide range of applications, e.g. self-driving cars, where safety and lives are at stake. Recently, the robustness of skeleto…
Talking Head from Speech Audio using a Pre-trained Image Generator
Mohammed M. Alghamdi, He Wang, Andrew J. Bulpitt +1
We propose a novel method for generating high-resolution videos of talking-heads from speech audio and a single 'identity' image. Our method is based on a convolutional neural netw…
Exploring the GLIDE model for Human Action-effect Prediction
Fangjun Li, David C. Hogg, Anthony G. Cohn
We address the following action-effect prediction task. Given an image depicting an initial state of the world and an action expressed in text, predict an image depicting the state…
Anomaly detection using prediction error with Spatio-Temporal Convolutional LSTM
Hanh Thi Minh Tran, David Hogg
In this paper, we propose a novel method for video anomaly detection motivated by an existing architecture for sequence-to-sequence prediction and reconstruction using a spatio-tem…
Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation
Rebecca S Stone, Nishant Ravikumar, Andrew J Bulpitt +1
Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowled…
Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
He Wang, Feixiang He, Zhexi Peng +4
Action recognition has been heavily employed in many applications such as autonomous vehicles, surveillance, etc, where its robustness is a primary concern. In this paper, we exami…
SMART: Skeletal Motion Action Recognition aTtack
He Wang, Feixiang He, Zhexi Peng +4
Adversarial attack has inspired great interest in computer vision, by showing that classification-based solutions are prone to imperceptible attack in many tasks. In this paper, we…
O2A: One-shot Observational learning with Action vectors
Leo Pauly, Wisdom C. Agboh, David C. Hogg +1
We present O2A, a novel method for learning to perform robotic manipulation tasks from a single (one-shot) third-person demonstration video. To our knowledge, it is the first time…
CLAD: A Complex and Long Activities Dataset with Rich Crowdsourced Annotations
Jawad Tayyub, Majd Hawasly, David C. Hogg +1
This paper introduces a novel activity dataset which exhibits real-life and diverse scenarios of complex, temporally-extended human activities and actions. The dataset presents a s…
The STRANDS Project: Long-Term Autonomy in Everyday Environments
Nick Hawes, Chris Burbridge, Ferdian Jovan +30
Thanks to the efforts of the robotics and autonomous systems community, robots are becoming ever more capable. There is also an increasing demand from end-users for autonomous serv…
Personalizing Human Video Pose Estimation
James Charles, Tomas Pfister, Derek Magee +2
We propose a personalized ConvNet pose estimator that automatically adapts itself to the uniqueness of a person's appearance to improve pose estimation in long videos. We make the…