Search Results for author:
Found 26 papers, 8 papers with code
Latent Bernoulli Autoencoder
In this work, we pose a question whether it is possible to design and train an autoencoder model in an end-to-end fashion to learn latent representations in multivariate Bernoulli space, and achieve performance comparable with the current state-of-the-art variational methods.
Dynamic Distinction Learning: Adaptive Pseudo Anomalies for Video Anomaly Detection
We introduce Dynamic Distinction Learning (DDL) for Video Anomaly Detection, a novel video anomaly detection methodology that combines pseudo-anomalies, dynamic anomaly weighting, and a distinction loss function to improve detection accuracy.
DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment
To this end, in this paper we present DiffusionAct, a novel method that leverages the photo-realistic image generation of diffusion models to perform neural face reenactment.
An AI-Assisted Skincare Routine Recommendation System in XR
This data is then used to train the CNN model, which recognises the skin type and existing issues and allows the recommendation engine to suggest personalised skin care products.
Evaluating the Energy Efficiency of Few-Shot Learning for Object Detection in Industrial Settings
In the ever-evolving era of Artificial Intelligence (AI), model performance has constituted a key metric driving innovation, leading to an exponential growth in model size and complexity.
Toward Green and Human-Like Artificial Intelligence: A Complete Survey on Contemporary Few-Shot Learning Approaches
Despite deep learning's widespread success, its data-hungry and computationally expensive nature makes it impractical for many data-constrained real-world applications.
One-shot Neural Face Reenactment via Finding Directions in GAN's Latent Space
Moreover, we show that by embedding real images in the GAN latent space, our method can be successfully used for the reenactment of real-world faces.
HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces
In this paper, we present our method for neural face reenactment, called HyperReenact, that aims to generate realistic talking head images of a source identity, driven by a target facial pose.
Evaluation of Environmental Conditions on Object Detection using Oriented Bounding Boxes for AR Applications
The objective of augmented reality (AR) is to add digital content to natural images and videos to create an interactive experience between the user and the environment.
StyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face Reenactment
In this paper we address the problem of neural face reenactment, where, given a pair of a source and a target facial image, we need to transfer the target's pose (defined as the head pose and its facial expressions) to the source image, by preserving at the same time the source's identity characteristics (e. g., facial shape, hair style, etc), even in the challenging case where the source and the target faces belong to different identities.
Finding Directions in GAN's Latent Space for Neural Face Reenactment
Moreover, we show that by embedding real images in the GAN latent space, our method can be successfully used for the reenactment of real-world faces.
Content-aware Density Map for Crowd Counting and Density Estimation
Precise knowledge about the size of a crowd, its density and flow can provide valuable information for safety and security applications, event planning, architectural design and to analyze consumer behavior.
Scene and Environment Monitoring Using Aerial Imagery and Deep Learning
In this paper, a review of studies applying deep learning on UAV imagery for smart farming is presented.
Iterative Self-Learning: Semi-Supervised Improvement to Dataset Volumes and Model Accuracy
A novel semi-supervised learning technique is introduced based on a simple iterative learning cycle together with learned thresholding techniques and an ensemble decision support system.
Smart IoT Cameras for Crowd Analysis based on augmentation for automatic pedestrian detection, simulation and annotation
In order to provide related behavioural models, simulation and tracking approaches have been considered in the literature.
Semi-supervised GAN for Classification of Multispectral Imagery Acquired by UAVs
The results by the proposed semi-supervised GAN achieves high classification accuracy and demonstrates the potential of GAN-based methods for the challenging task of multispectral image classification.
Features Extraction Based on an Origami Representation of 3D Landmarks
The performance evaluation demonstrates an improvement on facial emotion classification (accuracy and F1 score) that indicates the superiority of the proposed methodology.
A Comparison of Embedded Deep Learning Methods for Person Detection
Recent advancements in parallel computing, GPU technology and deep learning provide a new platform for complex image processing tasks such as person detection to flourish.
Summarizing Videos with Attention
In this work we propose a novel method for supervised, keyshots based video summarization by applying a conceptually simple and computationally efficient soft, self-attention mechanism.
Ranked #3 on
Video Summarization
on TvSum
(using extra training data)
Object 3D Reconstruction based on Photometric Stereo and Inverted Rendering
Our suggested approach is to recover scene properties in the presence of indirect illumination.
Machine learning architectures to predict motion sickness using a Virtual Reality rollercoaster simulation tool
An application that lets users create rollercoasters directly in VR, share them with other users and ride and rate them is used to gather real-time data related to the in-game behaviour of the player, the track itself and users' ratings based on a Simulator Sickness Questionnaire (SSQ) integrated into the application.
Asymmetric Bilateral Phase Correlation for Optical Flow Estimation in the Frequency Domain
We address the problem of motion estimation in images operating in the frequency domain.
Superframes, A Temporal Video Segmentation
The goal of video segmentation is to turn video data into a set of concrete motion clusters that can be easily interpreted as building blocks of the video.
AMNet: Memorability Estimation with Attention
Further on we study the impact of the attention mechanism on the memorability estimation and evaluate our network on the SUN Memorability and the LaMem datasets.
A Human and Group Behaviour Simulation Evaluation Framework utilising Composition and Video Analysis
In this work we present the modular Crowd Simulation Evaluation through Composition framework (CSEC) which provides a quantitative comparison between different pedestrian and crowd simulation approaches.
Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression
Our CNN works with just a single 2D facial image, does not require accurate alignment nor establishes dense correspondence between images, works for arbitrary facial poses and expressions, and can be used to reconstruct the whole 3D facial geometry (including the non-visible parts of the face) bypassing the construction (during training) and fitting (during testing) of a 3D Morphable Model.
Ranked #2 on
3D Face Reconstruction
on Florence
