Search Results for author:
Found 31 papers, 8 papers with code
PLOT-TAL -- Prompt Learning with Optimal Transport for Few-Shot Temporal Action Localization
This paper introduces a novel approach to temporal action localization (TAL) in few-shot learning.
A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images using a GAN
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.
ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet
This paper introduces ViscoNet, a novel method that enhances text-to-image human generation models with visual prompting.
ZeST-NeRF: Using temporal aggregation for Zero-Shot Temporal NeRFs
Recent approaches have had great success at performing novel view image synthesis of static scenes.
Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization
Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos.
DECORAIT -- DECentralized Opt-in/out Registry for AI Training
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.
MOFO: MOtion FOcused Self-Supervision for Video Understanding
Despite the importance of motion in supervised learning techniques for action recognition, SSL methods often do not explicitly consider motion information in videos.
DIFF-NST: Diffusion Interleaving For deFormable Neural Style Transfer
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.
UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer
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)
ALADIN-NST: Self-supervised disentangled representation learning of artistic style through Neural Style Transfer
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.
NeAT: Neural Artistic Tracing for Beautiful Style Transfer
As a component of curating this data, we present a novel model able to classify if an image is stylistic.
EKILA: Synthetic Media Provenance and Attribution for Generative Art
We present EKILA; a decentralized framework that enables creatives to receive recognition and reward for their contributions to generative AI (GenAI).
SVS: Adversarial refinement for sparse novel 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 significant.
HyperNST: Hyper-Networks for Neural Style Transfer
We present HyperNST; a neural style transfer (NST) technique for the artistic stylization of images, based on Hyper-networks and the StyleGAN2 architecture.
Two-Stream Transformer Architecture for Long Video Understanding
Pure vision transformer architectures are highly effective for short video classification and action recognition tasks.
Light-weight spatio-temporal graphs for segmentation and ejection fraction prediction in cardiac ultrasound
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
SaiNet: Stereo aware inpainting behind objects with generative networks
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.
StyleBabel: Artistic Style Tagging and Captioning
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.
KPE: Keypoint Pose Encoding for Transformer-based Image Generation
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.
Human-like Relational Models for Activity Recognition in Video
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.
ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity
We present ALADIN (All Layer AdaIN); a novel architecture for searching images based on the similarity of their artistic style.
Rethinking movie genre classification with fine-grained semantic clustering
We expand these 'coarse' genre labels by identifying 'fine-grained' semantic information within the multi-modal content of movies.
Neural Architecture Search for Deep Image Prior
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).
Automated Left Ventricle Dimension Measurement in 2D Cardiac Ultrasound via an Anatomically Meaningful CNN Approach
Treating the problem as a landmark detection problem, we propose a modified U-Net CNN architecture to generate heatmaps of likely coordinate locations.
Doppler Spectrum Classification with CNNs via Heatmap Location Encoding and a Multi-head Output Layer
We analyze example images that fall outside of our proposed classes to show our confidence metric can prevent many misclassifications.
Semantic Estimation of 3D Body Shape and Pose using Minimal Cameras
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
Volumetric performance capture from minimal camera viewpoints
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.
Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling
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
Disentangling Structure and Aesthetics for Style-Aware Image Completion
Content-aware image completion or in-painting is a fundamental tool for the correction of defects or removal of objects in images.
Total capture: 3D human pose estimation fusing video and inertial sensors
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
Image and Video Mining through Online Learning
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.
