Interests
- Computer Vision
- Deep Learning
Latest
- MiDaS: A Large-Scale Minecraft Dataset for Non-Natural Image Benchmarking
- Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies
- Creating Diverse Play-Style-Centric Agents through Behavioural Cloning
- Overlooked Implications of the Reconstruction Loss for VAE Disentanglement
- Revisiting the Role of Relearning in Semantic Dementia
- Generating Interpretable Play-style Descriptions through Deep Unsupervised Clustering of Trajectories
- On The Specialization of Neural Modules
- Improved Action Prediction through Multiple Model Processing of Player Trajectories
- Play-style Identification through Deep Unsupervised Clustering of Trajectories
- Accounting for the Sequential Nature of States to Learn Representations in Reinforcement Learning
- Constructing a Visual Dataset to Study the Effects of Spatial Apartheid in South Africa
- Improving Pose Estimation through Contextual Activity Fusion
- Generative Adversarial Networks for Global Illumination and Indirect Lighting as a Replacement for Ray-tracing in Older GPU Hardware
- Defect Detection and Quantification in Electroluminescence Images of Solar PV Modules using U-net Semantic Segmentation
- Confident in the Crowd: Bayesian Inference to Improve Data Labelling in Crowdsourcing
- Quantisation and Pruning for Neural Network Compression and Regularisation
- A Comparison Between Fully Connected and Deconvolutional Layers for Road Segmentation from Satellite Imagery
- Single-labelled Music Genre Classification Using Content-Based Features