Neural Style Transfer (NST) is the field of study applying neural techni...
Representation learning aims to discover individual salient features of ...
Style transfer is the task of reproducing the semantic contents of a sou...
We present EKILA; a decentralized framework that enables creatives to re...
Data hiding such as steganography and invisible watermarking has importa...
We propose VADER, a spatio-temporal matching, alignment, and change
summ...
We propose PARASOL, a multi-modal synthesis model that enables disentang...
We propose a self-supervised learning approach for videos that learns
re...
We present HyperNST; a neural style transfer (NST) technique for the art...
As tools for content editing mature, and artificial intelligence (AI) ba...
Rapid advances in Generative Adversarial Networks (GANs) raise new chall...
We present SImProv - a scalable image provenance framework to match a qu...
We present CoGS, a novel method for the style-conditioned, sketch-driven...
We present StyleBabel, a unique open access dataset of natural language
...
Image attribution – matching an image back to a trusted source – is an
e...
We present VPN - a content attribution method for recovering provenance
...
Scene Designer is a novel method for searching and generating images usi...
Images tell powerful stories but cannot always be trusted. Matching imag...
We present an algorithm for searching image collections using free-hand
...
We present Magic Layouts; a method for parsing screenshots or hand-drawn...
We present ALADIN (All Layer AdaIN); a novel architecture for searching
...
We propose Geo-PIFu, a method to recover a 3D mesh from a monocular colo...
Sketchformer is a novel transformer-based representation for encoding
fr...
We present a neural architecture search (NAS) technique to enhance the
p...
We propose a novel video inpainting algorithm that simultaneously
halluc...
We present an approach to accurately estimate high fidelity markerless 3...
We present a novel method for generating robust adversarial image exampl...
We present a novel blockchain based service for proving the provenance o...
We present ARCHANGEL; a novel distributed ledger based system for assuri...
LiveSketch is a novel algorithm for searching large image collections us...
We present a convolutional autoencoder that enables high fidelity volume...
We present a method for simultaneously estimating 3D human pose and body...
We present ARCHANGEL; a de-centralised platform for ensuring the long-te...
We propose and evaluate several triplet CNN architectures for measuring ...