b'qut'

research

∙ 07/21/2021

Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics

We present Bayesian Controller Fusion (BCF): a hybrid control strategy t...

Krishan Rana, et al. ∙

research

∙ 12/16/2019

Predicting the Future: A Jointly Learnt Model for Action Anticipation

Inspired by human neurological structures for action anticipation, we pr...

Harshala Gammulle, et al. ∙

research

∙ 04/16/2019

Are State-of-the-art Visual Place Recognition Techniques any Good for Aerial Robotics?

Visual Place Recognition (VPR) has seen significant advances at the fron...

Mubariz Zaffar, et al. ∙

research

∙ 12/18/2018

GD-GAN: Generative Adversarial Networks for Trajectory Prediction and Group Detection in Crowds

This paper presents a novel deep learning framework for human trajectory...

Tharindu Fernando, et al. ∙

research

∙ 02/28/2019

Robust Re-identification of Manta Rays from Natural Markings by Learning Pose Invariant Embeddings

Visual identification of individual animals that bear unique natural bod...

Olga Moskvyak, et al. ∙

research

∙ 09/20/2019

Fine-grained Action Segmentation using the Semi-Supervised Action GAN

In this paper we address the problem of continuous fine-grained action s...

Harshala Gammulle, et al. ∙

research

∙ 05/30/2020

QuLBIT: Quantum-Like Bayesian Inference Technologies for Cognition and Decision

This paper provides the foundations of a unified cognitive decision-maki...

Catarina Moreira, et al. ∙

research

∙ 12/01/2021

Point Cloud Segmentation Using Sparse Temporal Local Attention

Point clouds are a key modality used for perception in autonomous vehicl...

Joshua Knights, et al. ∙

research

∙ 03/15/2022

What's in the Black Box? The False Negative Mechanisms Inside Object Detectors

In object detection, false negatives arise when a detector fails to dete...

Dimity Miller, et al. ∙

research

∙ 02/21/2020

An Investigation of Interpretability Techniques for Deep Learning in Predictive Process Analytics

This paper explores interpretability techniques for two of the most succ...

Catarina Moreira, et al. ∙

research

∙ 03/11/2020

Multiplicative Controller Fusion: A Hybrid Navigation Strategy For Deployment in Unknown Environments

Learning-based approaches often outperform hand-coded algorithmic soluti...

Krishan Rana, et al. ∙

research

∙ 11/07/2018

A Holistic Visual Place Recognition Approach using Lightweight CNNs for Severe ViewPoint and Appearance Changes

Recently, deep and complex Convolutional Neural Network (CNN) architectu...

Ahmad Khaliq, et al. ∙

research

∙ 09/18/2019

CAMAL: Context-Aware Multi-scale Attention framework for Lightweight Visual Place Recognition

In the last few years, Deep Convolutional Neural Networks (D-CNNs) have ...

Ahmad Khaliq, et al. ∙

research

∙ 09/03/2021

Building Interpretable Models for Business Process Prediction using Shared and Specialised Attention Mechanisms

In this paper, we address the "black-box" problem in predictive process ...

Bemali Wickramanayake, et al. ∙

research

∙ 01/09/2020

Learning landmark guided embeddings for animal re-identification

Re-identification of individual animals in images can be ambiguous due t...

Olga Moskvyak, et al. ∙

research

∙ 01/23/2020

Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded Representations

Visual place recognition algorithms trade off three key characteristics:...

Sourav Garg, et al. ∙

research

∙ 10/24/2018

A Binary Optimization Approach for Constrained K-Means Clustering

K-Means clustering still plays an important role in many computer vision...

Huu Le, et al. ∙

research

∙ 04/28/2021

Pose-driven Attention-guided Image Generation for Person Re-Identification

Person re-identification (re-ID) concerns the matching of subject images...

Amena Khatun, et al. ∙

research

∙ 08/19/2021

FSNet: A Failure Detection Framework for Semantic Segmentation

Semantic segmentation is an important task that helps autonomous vehicle...

Quazi Marufur Rahman, et al. ∙

research

∙ 06/27/2019

BTEL: A Binary Tree Encoding Approach for Visual Localization

Visual localization algorithms have achieved significant improvements in...

Huu Le, et al. ∙

research

∙ 07/05/2022

SESS: Saliency Enhancing with Scaling and Sliding

High-quality saliency maps are essential in several machine learning app...

Osman Tursun, et al. ∙

research

∙ 08/01/2019

Visual Place Recognition for Aerial Robotics: Exploring Accuracy-Computation Trade-off for Local Image Descriptors

Visual Place Recognition (VPR) is a fundamental yet challenging task for...

Bruno Ferrarini, et al. ∙

research

∙ 01/16/2020

Predicting Target Feature Configuration of Non-stationary Objects for Grasping with Image-Based Visual Servoing

In this paper we consider the problem of the final approach stage of clo...

Jesse Haviland, et al. ∙

research

∙ 05/17/2020

VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change

Visual Place Recognition (VPR) is the process of recognising a previousl...

Mubariz Zaffar, et al. ∙

research

∙ 02/18/2022

MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery

Visual Place Recognition (VPR) is a crucial component of 6-DoF localizat...

Ahmad Khaliq, et al. ∙

research

∙ 06/28/2022

When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation

Self-supervised deep learning methods for joint depth and ego-motion est...

Madhu Vankadari, et al. ∙

research

∙ 02/08/2021

An Efficient Framework for Zero-Shot Sketch-Based Image Retrieval

Recently, Zero-shot Sketch-based Image Retrieval (ZS-SBIR) has attracted...

Osman Tursun, et al. ∙

research

∙ 10/11/2018

Towards the Targeted Environment-Specific Evolution of Robot Components

This research considers the task of evolving the physical structure of a...

Jack Collins, et al. ∙

research

∙ 11/08/2018

Memorable Maps: A Framework for Re-defining Places in Visual Place Recognition

A novel cognition-inspired, agnostic framework is proposed for building ...

Mubariz Zaffar, et al. ∙

research

∙ 08/11/2021

Zero-Shot Domain Adaptation with a Physics Prior

We explore the zero-shot setting for day-night domain adaptation. The tr...

Attila Lengyel, et al. ∙

research

∙ 10/23/2018

Large scale visual place recognition with sub-linear storage growth

Robotic and animal mapping systems share many of the same objectives and...

Huu Le, et al. ∙

research

∙ 03/21/2019

Levelling the Playing Field: A Comprehensive Comparison of Visual Place Recognition Approaches under Changing Conditions

In recent years there has been significant improvement in the capability...

Mubariz Zaffar, et al. ∙

research

∙ 12/16/2019

MTRNet++: One-stage Mask-based Scene Text Eraser

A precise, controllable, interpretable and easily trainable text removal...

Osman Tursun, et al. ∙

research

∙ 12/07/2016

Predictive Business Process Monitoring with LSTM Neural Networks

Predictive business process monitoring methods exploit logs of completed...

Niek Tax, et al. ∙

research

∙ 12/10/2021

Hyperdimensional Feature Fusion for Out-Of-Distribution Detection

We introduce powerful ideas from Hyperdimensional Computing into the cha...

Samuel Wilson, et al. ∙

research

∙ 11/20/2017

Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments

A robot that can carry out a natural-language instruction has been a dre...

Peter Anderson, et al. ∙

research

∙ 11/28/2017

One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay

Recently, model-free reinforcement learning algorithms have been shown t...

Jake Bruce, et al. ∙

research

∙ 11/17/2017

Detecting hip fractures with radiologist-level performance using deep neural networks

We developed an automated deep learning system to detect hip fractures f...

William Gale, et al. ∙

research

∙ 09/18/2017

Sim-to-real Transfer of Visuo-motor Policies for Reaching in Clutter: Domain Randomization and Adaptation with Modular Networks

A modular method is proposed to learn and transfer visuo-motor policies ...

Fangyi Zhang, et al. ∙

research

∙ 03/12/2017

Tree Memory Networks for Modelling Long-term Temporal Dependencies

In the domain of sequence modelling, Recurrent Neural Networks (RNN) hav...

Tharindu Fernando, et al. ∙

research

∙ 10/27/2017

Deterministic Approximate Methods for Maximum Consensus Robust Fitting

Maximum consensus estimation plays a critically important role in robust...

Huu Le, et al. ∙

research

∙ 10/18/2017

Dropout Sampling for Robust Object Detection in Open-Set Conditions

Dropout Variational Inference, or Dropout Sampling, has been recently pr...

Dimity Miller, et al. ∙

research

∙ 06/17/2017

Bayesian Conditional Generative Adverserial Networks

Traditional GANs use a deterministic generator function (typically a neu...

Ehsan Abbasnejad, et al. ∙

research

∙ 09/07/2017

Towards high-throughput 3D insect capture for species discovery and diagnostics

Digitisation of natural history collections not only preserves precious ...

Chuong Nguyen, et al. ∙

research

∙ 05/15/2017

Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination

This paper introduces an end-to-end fine-tuning method to improve hand-e...

Fangyi Zhang, et al. ∙

research

∙ 07/23/2017

Compact Model Representation for 3D Reconstruction

3D reconstruction from 2D images is a central problem in computer vision...

Jhony K. Pontes, et al. ∙

research

∙ 10/21/2016

Modular Deep Q Networks for Sim-to-real Transfer of Visuo-motor Policies

While deep learning has had significant successes in computer vision tha...

Fangyi Zhang, et al. ∙

research

∙ 10/19/2016

Hit-and-Run for Sampling and Planning in Non-Convex Spaces

We propose the Hit-and-Run algorithm for planning and sampling problems ...

Yasin Abbasi-Yadkori, et al. ∙

research

∙ 03/21/2017

Episode-Based Active Learning with Bayesian Neural Networks

We investigate different strategies for active learning with Bayesian de...

Feras Dayoub, et al. ∙

research

∙ 09/12/2016

DESPOT: Online POMDP Planning with Regularization

The partially observable Markov decision process (POMDP) provides a prin...

Nan Ye, et al. ∙

qut

Featured Researchers