The elements of end-to-end deep face recognition: A survey of recent advances
Face recognition (FR) is one of the most popular and long-standing topics in computer
vision. With the recent development of deep learning techniques and large-scale datasets …
vision. With the recent development of deep learning techniques and large-scale datasets …
Arcface: Additive angular margin loss for deep face recognition
One of the main challenges in feature learning using Deep Convolutional Neural Networks
(DCNNs) for large-scale face recognition is the design of appropriate loss functions that can …
(DCNNs) for large-scale face recognition is the design of appropriate loss functions that can …
The new generation brain-inspired sparse learning: A comprehensive survey
In recent years, the enormous demand for computing resources resulting from massive data
and complex network models has become the limitation of deep learning. In the large-scale …
and complex network models has become the limitation of deep learning. In the large-scale …
A survey of face recognition
X Wang, J Peng, S Zhang, B Chen, Y Wang… - arXiv preprint arXiv …, 2022 - arxiv.org
Recent years witnessed the breakthrough of face recognition with deep convolutional neural
networks. Dozens of papers in the field of FR are published every year. Some of them were …
networks. Dozens of papers in the field of FR are published every year. Some of them were …
Deep learning for camera calibration and beyond: A survey
Camera calibration involves estimating camera parameters to infer geometric features from
captured sequences, which is crucial for computer vision and robotics. However …
captured sequences, which is crucial for computer vision and robotics. However …
Boosted Additive Angular Margin Loss for breast cancer diagnosis from histopathological images
P Alirezazadeh, F Dornaika - Computers in Biology and Medicine, 2023 - Elsevier
Pathologists use biopsies and microscopic examination to accurately diagnose breast
cancer. This process is time-consuming, labor-intensive, and costly. Convolutional neural …
cancer. This process is time-consuming, labor-intensive, and costly. Convolutional neural …
Mitigating poor data quality impact with federated unlearning for human-centric metaverse
Federated Learning (FL), which has been employed to train machine learning models on the
data with a distributed manner, could enhance the immersive user experience for the human …
data with a distributed manner, could enhance the immersive user experience for the human …
Hybrid attention network and center-guided non-maximum suppression for occluded face detection
M Jin, H Li, Z Xia - Multimedia Tools and Applications, 2023 - Springer
The face detection technique has obtained significant development with the huge
application of convolutional neural networks. However, various types of occlusion are …
application of convolutional neural networks. However, various types of occlusion are …
The Aeroplane and Undercarriage Detection Based on Attention Mechanism and Multi‐Scale Features Processing
R Gao, S Zhang, H Wang, J Zhang… - Mobile Information …, 2022 - Wiley Online Library
Undercarriage device is one of the essential parts of an aeroplane, and accurate detection
of whether the aeroplane undercarriage is operating normally can effectively avoid …
of whether the aeroplane undercarriage is operating normally can effectively avoid …
SACN: a novel rotating face detector based on architecture search
A Song, X Xu, X Zhai - Electronics, 2021 - mdpi.com
Rotation-Invariant Face Detection (RIPD) has been widely used in practical applications;
however, the problem of the adjusting of the rotation-in-plane (RIP) angle of the human face …
however, the problem of the adjusting of the rotation-in-plane (RIP) angle of the human face …