Related papers: GADS: A Super Lightweight Model for Head Pose Esti…
Human pose estimation from image and video is a vital task in many multimedia applications. Previous methods achieve great performance but rarely take efficiency into consideration, which makes it difficult to implement the networks on…
Currently, every 1 in 54 children have been diagnosed with Autism Spectrum Disorder (ASD), which is 178% higher than it was in 2000. An early diagnosis and treatment can significantly increase the chances of going off the spectrum and…
Recent advancements in Low-Light Image Enhancement (LLIE) have focused heavily on Diffusion Probabilistic Models, which achieve high perceptual quality but suffer from significant computational latency (often exceeding 2-4 seconds per…
Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in the computer vision community. However, most algorithms are designed for faces in small to medium poses…
Deep learning approaches have achieved highly accurate face recognition by training the models with very large face image datasets. Unlike the availability of large 2D face image datasets, there is a lack of large 3D face datasets available…
Micro-expression recognition (MER) is valuable because micro-expressions (MEs) can reveal genuine emotions. Most works take image sequences as input and cannot effectively explore ME information because subtle ME-related motions are easily…
State-of-the-art methods for 3D hand pose estimation from depth images require large amounts of annotated training data. We propose to model the statistical relationships of 3D hand poses and corresponding depth images using two deep…
Head orientation is a challenging Computer Vision problem that has been extensively researched having a wide variety of applications. However, current state-of-the-art systems still underperform in the presence of occlusions and are…
We develop a robust multi-scale structure-aware neural network for human pose estimation. This method improves the recent deep conv-deconv hourglass models with four key improvements: (1) multi-scale supervision to strengthen contextual…
Heatmap regression has been used for landmark localization for quite a while now. Most of the methods use a very deep stack of bottleneck modules for heatmap classification stage, followed by heatmap regression to extract the keypoints. In…
Instance selection (IS) is a crucial technique in machine learning that aims to reduce dataset size while maintaining model performance. This paper introduces a novel method called Graph Attention-based Instance Selection (GAIS), which…
We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs). We first compare and analyse different loss functions including L2, L1 and smooth L1. The analysis of these…
High spectral resolution imagery of the Earth's surface enables users to monitor changes over time in fine-grained scale, playing an increasingly important role in agriculture, defense, and emergency response. However, most current…
Gaze estimation, which predicts gaze direction, commonly faces the challenge of interference from complex gaze-irrelevant information in face images. In this work, we propose DMAGaze, a novel gaze estimation framework that exploits…
CNN-based face recognition models have brought remarkable performance improvement, but they are vulnerable to adversarial perturbations. Recent studies have shown that adversaries can fool the models even if they can only access the models'…
Depth cameras allow to set up reliable solutions for people monitoring and behavior understanding, especially when unstable or poor illumination conditions make unusable common RGB sensors. Therefore, we propose a complete framework for the…
We explore techniques for eye gaze estimation using machine learning. Eye gaze estimation is a common problem for various behavior analysis and human-computer interfaces. The purpose of this work is to discuss various model types for eye…
Face image super-resolution aims to recover high-resolution facial images from severely degraded inputs. Under extreme upscaling factors, fine facial details are often lost, making accurate reconstruction challenging. Existing methods…
In general, human pose estimation methods are categorized into two approaches according to their architectures: regression (i.e., heatmap-free) and heatmap-based methods. The former one directly estimates precise coordinates of each…
Face frontalization provides an effective and efficient way for face data augmentation and further improves the face recognition performance in extreme pose scenario. Despite recent advances in deep learning-based face synthesis approaches,…