3d face recognition: Two decades of progress and prospects
Three-dimensional (3D) face recognition has been extensively investigated in the last two
decades due to its wide range of applications in many areas, such as security and forensics …
decades due to its wide range of applications in many areas, such as security and forensics …
Depth as attention for face representation learning
H Uppal, A Sepas-Moghaddam… - IEEE Transactions …, 2021 - ieeexplore.ieee.org
Face representation learning solutions have recently achieved great success for various
applications such as verification and identification. However, face recognition approaches …
applications such as verification and identification. However, face recognition approaches …
A systematic comparison of depth map representations for face recognition
Nowadays, we are witnessing the wide diffusion of active depth sensors. However, the
generalization capabilities and performance of the deep face recognition approaches that …
generalization capabilities and performance of the deep face recognition approaches that …
Two-level attention-based fusion learning for rgb-d face recognition
H Uppal, A Sepas-Moghaddam… - 2020 25th …, 2021 - ieeexplore.ieee.org
With recent advances in RGB-D sensing technologies as well as improvements in machine
learning and fusion techniques, RGB-D facial recognition has become an active area of …
learning and fusion techniques, RGB-D facial recognition has become an active area of …
Predicting the politics of an image using webly supervised data
C Thomas, A Kovashka - Advances in neural information …, 2019 - proceedings.neurips.cc
The news media shape public opinion, and often, the visual bias they contain is evident for
human observers. This bias can be inferred from how different media sources portray …
human observers. This bias can be inferred from how different media sources portray …
Detecting morphing attacks via continual incremental training
Scenarios in which restrictions in data transfer and storage limit the possibility to compose a
single dataset–also exploiting different data sources–to perform a batch-based training …
single dataset–also exploiting different data sources–to perform a batch-based training …
Siamese Neural Pointnet: 3D Face Verification under Pose Interference and Partial Occlusion
Face verification based on ordinary 2D RGB images has been widely used in daily life.
However, the quality of ordinary 2D RGB images is limited by illumination, and they lack …
However, the quality of ordinary 2D RGB images is limited by illumination, and they lack …
Cross-modality personalization for retrieval
N Murrugarra-Llerena… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Existing captioning and gaze prediction approaches do not consider the multiple facets of
personality that affect how a viewer extracts meaning from an image. While there are …
personality that affect how a viewer extracts meaning from an image. While there are …
Driver face verification with depth maps
Face verification is the task of checking if two provided images contain the face of the same
person or not. In this work, we propose a fully-convolutional Siamese architecture to tackle …
person or not. In this work, we propose a fully-convolutional Siamese architecture to tackle …
Boosting depth-based face recognition from a quality perspective
Face recognition using depth data has attracted increasing attention from both academia
and industry in the past five years. Previous works show a huge performance gap between …
and industry in the past five years. Previous works show a huge performance gap between …