no code implementations • 27 Mar 2024 • Edward Fish, Jon Weinbren, Andrew Gilbert
This paper introduces a novel approach to temporal action localization (TAL) in few-shot learning.
no code implementations • 8 Mar 2024 • Cristiana Tiago, Andrew Gilbert, Ahmed S. Beela, Svein Arne Aase, Sten Roar Snare, Jurica Sprem
A quantitative analysis of the 3D segmentations given by the models trained with the synthetic images indicated the potential use of this GAN approach to generate 3D synthetic data, use the data to train DL models for different clinical tasks, and therefore tackle the problem of scarcity of 3D labeled echocardiography datasets.
1 code implementation • 5 Dec 2023 • Soon Yau Cheong, Armin Mustafa, Andrew Gilbert
This paper introduces ViscoNet, a novel method that enhances text-to-image human generation models with visual prompting.
no code implementations • 30 Nov 2023 • Violeta Menéndez González, Andrew Gilbert, Graeme Phillipson, Stephen Jolly, Simon Hadfield
Recent approaches have had great success at performing novel view image synthesis of static scenes.
no code implementations • 5 Oct 2023 • Edward Fish, Jon Weinbren, Andrew Gilbert
Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos.
no code implementations • 25 Sep 2023 • Kar Balan, Alex Black, Simon Jenni, Andrew Gilbert, Andy Parsons, John Collomosse
We report a prototype of DECORAIT, which explores hierarchical clustering and a combination of on/off-chain storage to create a scalable decentralized registry to trace the provenance of GenAI training data in order to determine training consent and reward creatives who contribute that data.
1 code implementation • 23 Aug 2023 • Mona Ahmadian, Frank Guerin, Andrew Gilbert
Despite the importance of motion in supervised learning techniques for action recognition, SSL methods often do not explicitly consider motion information in videos.
no code implementations • 9 Jul 2023 • Dan Ruta, Gemma Canet Tarrés, Andrew Gilbert, Eli Shechtman, Nicholas Kolkin, John Collomosse
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.
1 code implementation • 18 Apr 2023 • 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.
Ranked #1 on Pose Transfer on Deep-Fashion (FID metric)
no code implementations • 12 Apr 2023 • Dan Ruta, Gemma Canet Tarres, Alexander Black, Andrew Gilbert, John Collomosse
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 sample respective to its domain.
1 code implementation • 11 Apr 2023 • Dan Ruta, Andrew Gilbert, John Collomosse, Eli Shechtman, Nicholas Kolkin
As a component of curating this data, we present a novel model able to classify if an image is stylistic.
no code implementations • 10 Apr 2023 • Kar Balan, Shruti Agarwal, Simon Jenni, Andy Parsons, Andrew Gilbert, John Collomosse
We present EKILA; a decentralized framework that enables creatives to receive recognition and reward for their contributions to generative AI (GenAI).
1 code implementation • 14 Nov 2022 • Violeta Menéndez González, Andrew Gilbert, Graeme Phillipson, Stephen Jolly, Simon Hadfield
This is a view synthesis problem where the number of reference views is limited, and the baseline between target and reference view is significant.
no code implementations • 9 Aug 2022 • Dan Ruta, Andrew Gilbert, Saeid Motiian, Baldo Faieta, Zhe Lin, John Collomosse
We present HyperNST; a neural style transfer (NST) technique for the artistic stylization of images, based on Hyper-networks and the StyleGAN2 architecture.
no code implementations • 2 Aug 2022 • Edward Fish, Jon Weinbren, Andrew Gilbert
Pure vision transformer architectures are highly effective for short video classification and action recognition tasks.
1 code implementation • 6 Jul 2022 • Sarina Thomas, Andrew Gilbert, Guy Ben-Yosef
In particular, segmentations of the left ventricle can be used to derive ventricular volume, ejection fraction (EF) and other relevant measurements.
Ranked #2 on on Echonet-Dynamic
no code implementations • 14 May 2022 • Violeta Menéndez González, Andrew Gilbert, Graeme Phillipson, Stephen Jolly, Simon Hadfield
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.
no code implementations • 10 Mar 2022 • Dan Ruta, Andrew Gilbert, Pranav Aggarwal, Naveen Marri, Ajinkya Kale, Jo Briggs, Chris Speed, Hailin Jin, Baldo Faieta, Alex Filipkowski, Zhe Lin, John Collomosse
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 novel participatory method from experts studying at specialist art and design schools.
1 code implementation • 9 Mar 2022 • Soon Yau Cheong, Armin Mustafa, Andrew Gilbert
Therefore we propose a new method; Keypoint Pose Encoding (KPE); KPE is 10 times more memory efficient and over 73% faster at generating high quality images from text input conditioned on the pose.
no code implementations • 12 Jul 2021 • Joseph Chrol-Cannon, Andrew Gilbert, Ranko Lazic, Adithya Madhusoodanan, Frank Guerin
We apply the method to a challenging subset of the something-something dataset and achieve a more robust performance against neural network baselines on challenging activities.
no code implementations • ICCV 2021 • Dan Ruta, Saeid Motiian, Baldo Faieta, Zhe Lin, Hailin Jin, Alex Filipkowski, Andrew Gilbert, John Collomosse
We present ALADIN (All Layer AdaIN); a novel architecture for searching images based on the similarity of their artistic style.
no code implementations • 4 Dec 2020 • Edward Fish, Jon Weinbren, Andrew Gilbert
We expand these 'coarse' genre labels by identifying 'fine-grained' semantic information within the multi-modal content of movies.
2 code implementations • 14 Jan 2020 • Kary Ho, Andrew Gilbert, Hailin Jin, John Collomosse
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 Deep Image Prior (DIP).
no code implementations • 6 Nov 2019 • Andrew Gilbert, Marit Holden, Line Eikvil, Svein Arne Aase, Eigil Samset, Kristin McLeod
Treating the problem as a landmark detection problem, we propose a modified U-Net CNN architecture to generate heatmaps of likely coordinate locations.
no code implementations • 6 Nov 2019 • Andrew Gilbert, Marit Holden, Line Eikvil, Mariia Rakhmail, Aleksandar Babic, Svein Arne Aase, Eigil Samset, Kristin McLeod
We analyze example images that fall outside of our proposed classes to show our confidence metric can prevent many misclassifications.
no code implementations • 8 Aug 2019 • Andrew Gilbert, Matthew Trumble, Adrian Hilton, John Collomosse
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.
Ranked #163 on 3D Human Pose Estimation on Human3.6M
no code implementations • ECCV 2018 • Andrew Gilbert, Marco Volino, John Collomosse, Adrian Hilton
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 of camera views.
no code implementations • ECCV 2018 • Matthew Trumble, Andrew Gilbert, Adrian Hilton, John Collomosse
We present a method for simultaneously estimating 3D human pose and body shape from a sparse set of wide-baseline camera views.
Ranked #9 on 3D Human Pose Estimation on Total Capture
no code implementations • CVPR 2018 • Andrew Gilbert, John Collomosse, Hailin Jin, Brian Price
Content-aware image completion or in-painting is a fundamental tool for the correction of defects or removal of objects in images.
no code implementations • BMVC 2017 2017 • Matthew Trumble, Andrew Gilbert, Charles Malleson, Adrian Hilton, and John Collomosse
We incorporate this model within a dual stream network integrating pose embeddings derived from MVV and a forward kinematic solve of the IMU data.
Ranked #11 on 3D Human Pose Estimation on Total Capture
no code implementations • 9 Sep 2016 • Andrew Gilbert, Richard Bowden
On the UCF11 video dataset, the accuracy is 86. 7% despite using only 90 labelled examples from a dataset of over 1200 videos, instead of the standard 1122 training videos.