8 citations · 35 across the 20 of their papers we have counts for
21 papers
DECORAIT -- DECentralized Opt-in/out Registry for AI Training
Kar Balan, Alex Black, Simon Jenni +3
We present DECORAIT; a decentralized registry through which content creators may assert their right to opt in or out of AI training as well as receive reward for their contribution…
MOFO: MOtion FOcused Self-Supervision for Video Understanding
Mona Ahmadian, Frank Guerin, Andrew Gilbert
Self-supervised learning (SSL) techniques have recently produced outstanding results in learning visual representations from unlabeled videos. Despite the importance of motion in s…
DIFF-NST: Diffusion Interleaving For deFormable Neural Style Transfer
Dan Ruta, Gemma Canet Tarrés, Andrew Gilbert +3
Neural Style Transfer (NST) is the field of study applying neural techniques to modify the artistic appearance of a content image to match the style of a reference style image. Tra…
NeAT: Neural Artistic Tracing for Beautiful Style Transfer
Dan Ruta, Andrew Gilbert, John Collomosse +2
Style transfer is the task of reproducing the semantic contents of a source image in the artistic style of a second target image. In this paper, we present NeAT, a new state-of-the…
EKILA: Synthetic Media Provenance and Attribution for Generative Art
Kar Balan, Shruti Agarwal, Simon Jenni +3
We present EKILA; a decentralized framework that enables creatives to receive recognition and reward for their contributions to generative AI (GenAI). EKILA proposes a robust visua…
UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer
Soon Yau Cheong, Armin Mustafa, Andrew Gilbert
Text-to-image models (T2I) such as StableDiffusion have been used to generate high quality images of people. However, due to the random nature of the generation process, the person…
ALADIN-NST: Self-supervised disentangled representation learning of artistic style through Neural Style Transfer
Dan Ruta, Gemma Canet Tarres, Alexander Black +2
Representation learning aims to discover individual salient features of a domain in a compact and descriptive form that strongly identifies the unique characteristics of a given sa…
SVS: Adversarial refinement for sparse novel view synthesis
Violeta Menéndez González, Andrew Gilbert, Graeme Phillipson +2
This paper proposes Sparse View Synthesis. This is a view synthesis problem where the number of reference views is limited, and the baseline between target and reference view is si…
HyperNST: Hyper-Networks for Neural Style Transfer
Dan Ruta, Andrew Gilbert, Saeid Motiian +3
We present HyperNST; a neural style transfer (NST) technique for the artistic stylization of images, based on Hyper-networks and the StyleGAN2 architecture. Our contribution is a n…
Two-Stream Transformer Architecture for Long Video Understanding
Edward Fish, Jon Weinbren, Andrew Gilbert
Pure vision transformer architectures are highly effective for short video classification and action recognition tasks. However, due to the quadratic complexity of self attention a…
SaiNet: Stereo aware inpainting behind objects with generative networks
Violeta Menéndez González, Andrew Gilbert, Graeme Phillipson +2
In this work, we present an end-to-end network for stereo-consistent image inpainting with the objective of inpainting large missing regions behind objects. The proposed model cons…
StyleBabel: Artistic Style Tagging and Captioning
Dan Ruta, Andrew Gilbert, Pranav Aggarwal +9
We present StyleBabel, a unique open access dataset of natural language captions and free-form tags describing the artistic style of over 135K digital artworks, collected via a nov…
KPE: Keypoint Pose Encoding for Transformer-based Image Generation
Soon Yau Cheong, Armin Mustafa, Andrew Gilbert
Transformers have recently been shown to generate high quality images from text input. However, the existing method of pose conditioning using skeleton image tokens is computationa…
Human-like Relational Models for Activity Recognition in Video
Joseph Chrol-Cannon, Andrew Gilbert, Ranko Lazic +2
Video activity recognition by deep neural networks is impressive for many classes. However, it falls short of human performance, especially for challenging to discriminate activiti…
ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity
Dan Ruta, Saeid Motiian, Baldo Faieta +5
We present ALADIN (All Layer AdaIN); a novel architecture for searching images based on the similarity of their artistic style. Representation learning is critical to visual search…
Rethinking movie genre classification with fine-grained semantic clustering
Edward Fish, Jon Weinbren, Andrew Gilbert
Movie genre classification is an active research area in machine learning. However, due to the limited labels available, there can be large semantic variations between movies withi…
Neural Architecture Search for Deep Image Prior
Kary Ho, Andrew Gilbert, Hailin Jin +1
We present a neural architecture search (NAS) technique to enhance the performance of unsupervised image de-noising, in-painting and super-resolution under the recently proposed De…
Semantic Estimation of 3D Body Shape and Pose using Minimal Cameras
Andrew Gilbert, Matthew Trumble, Adrian Hilton +1
We aim to simultaneously estimate the 3D articulated pose and high fidelity volumetric occupancy of human performance, from multiple viewpoint video (MVV) with as few as two views.…
Volumetric performance capture from minimal camera viewpoints
Andrew Gilbert, Marco Volino, John Collomosse +1
We present a convolutional autoencoder that enables high fidelity volumetric reconstructions of human performance to be captured from multi-view video comprising only a small set o…
Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling
Matthew Trumble, Andrew Gilbert, Adrian Hilton +1
We present a method for simultaneously estimating 3D human pose and body shape from a sparse set of wide-baseline camera views. We train a symmetric convolutional autoencoder with…
Image and Video Mining through Online Learning
Andrew Gilbert, Richard Bowden
Within the field of image and video recognition, the traditional approach is a dataset split into fixed training and test partitions. However, the labelling of the training set is…