PhD Student @ AIML

hayden.faulkner _at_

about Me

I am a final year PhD student within The Australian Institute for Machine Learning at The University of Adelaide, in South Australia. I work heavily in the fields of Computer Vision, Machine Learning and Artificial Intelligence. I am currently focused on developing novel approaches to automatically understand and summarise videos. I have worked on image and video classification, detection, captioning and tracking with deep neural networks and big data. I am passionate about applying the latest techniques to solve real world problems, as well as effectively communicating ideas to both collegues and the broader community.


Computer Vision

Using computers to perform image and video processing. Extracting useful information from image data.

Machine Learning

Enabling computers to automatically learn from data to uncover trends and extract information otherwise unseen.

Neural Networks

Experience building and utilising many forms of neural networks, such as convolutional and recurrent neural networks.

App Development

Ability to turn the latest state of the art techniques into useful end user applications to solve real world problems.


TenniSet: A Dataset for Dense Fine-Grained Event Recognition, Localisation and Description

Proceedings of the 2017 International Conference on Digital Image Computing: Techniques and Applications

This paper introduces a new video understanding dataset which can be utilised for the related problems of event recognition, localisation and description in video. Our dataset consists of dense, well structured event annotations in untrimmed video of tennis matches. We also include highly detailed commentary style descriptions, which are heavily dependent on both the occurrence as well as the sequence of particular events. We use general deep learning techniques to acquire some initial baseline results on our dataset, without the need for explicit domain-specific assumptions.

AFL Player Detection and Tracking

Proceedings of the 2015 International Conference on Digital Image Computing: Techniques and Applications

This paper is an empirical study of the application of visual detection and tracking methods to the problem of locating and tracking all AFL players during a game. While most person detection and tracking algorithms are designed for pedestrians, we show that with appropriate modifications, state of the art methods can be adapted to a more challenging domain where motion is significantly more varied and occurs in a much wider area.

A Study of the Region Covariance Descriptor: Impact of Feature Selection and Image Transformations

Proceedings of the 2015 International Conference on Digital Image Computing: Techniques and Applications

We analyse experimentally the region covariance descriptor which has proven useful in numerous computer vision applications. The properties of the descriptor–despite its widespread deployment–are not well understood or documented. In an attempt to uncover key attributes of the descriptor, we characterise the interdependence between the choice of features and distance measures through a series of meticulously designed and performed experiments. Our results paint a rather complex picture and underscore the necessity for more extensive empirical and theoretical work. In light of our findings, there is reason to believe that the region covariance descriptor will prove useful for methods that perform image super-resolution, deblurring, and denoising based on matching and retrieval of image patches from an image dictionary.

Approximate Approaches to the Traveling Thief Problem

Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation

This study addresses the recently introduced Traveling Thief Problem (TTP) which combines the classical Traveling Salesman Problem (TSP) with the 0-1 Knapsack Problem (KP). The problem consists of a set of cities, each containing a set of available items with weights and profits. It involves searching for a permutation of the cities to visit and a decision on items to pick. A selected item contributes its profit to the overall profit at the price of higher transportation cost incurred by its weight. The objective is to maximize the resulting profit. We propose a number of problem-specific packing strategies run on top of TSP solutions derived by the Chained Lin-Kernighan heuristic. The investigations provided on the set of benchmark instances prove their rapidity and efficiency when compared with an approximate mixed integer programming based approach and state-of-the-art heuristic solutions from the literature.


PhD in Computer Science

Event Detection, Recognition & Summarisation from Video
Supervised by: Professor Anthony Dick & Professor Anton van den Hengel
Funded by the Data to Decisions CRC



Honours in Computer Science

Visual Tracking for Application to AFL Football [Thesis] [Poster]
Supervised by: Professor Anthony Dick
First Class, Top of Class

Graduate Certificate in Creative Arts (Visual Effects)

In conjunction with Rising Sun Pictures


2010 - 2012

Bachelor of Computer Graphics

GPA of 5.625


Three Minute Thesis Winner

2015, 2017
Among Data to Decisions CRC students

Google Prize for Honours

Highest score among peers in Honours year

Posts & Talks

POST: Extracting Frames FAST from a Video using OpenCV and Python

Read this story on Medium

TALK: Deep Learning for Computer Vision

Presented on behalf of the Data to Decisions CRC

Get in Touch