Fsa-net: Learning fine-grained structure aggregation for head pose estimation from a single image

TY Yang, YT Chen, YY Lin… - Proceedings of the …, 2019 - openaccess.thecvf.com
This paper proposes a method for head pose estimation from a single image. Previous
methods often predict head poses through landmark or depth estimation and would require …

Synergy between 3dmm and 3d landmarks for accurate 3d facial geometry

CY Wu, Q Xu, U Neumann - 2021 International Conference on …, 2021 - ieeexplore.ieee.org
This work studies learning from a synergy process of 3D Morphable Models (3DMM) and 3D
facial landmarks to predict complete 3D facial geometry, including 3D alignment, face …

Whenet: Real-time fine-grained estimation for wide range head pose

Y Zhou, J Gregson - arxiv preprint arxiv:2005.10353, 2020 - arxiv.org
We present an end-to-end head-pose estimation network designed to predict Euler angles
through the full range head yaws from a single RGB image. Existing methods perform well …

Learning probabilistic ordinal embeddings for uncertainty-aware regression

W Li, X Huang, J Lu, J Feng… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Uncertainty is the only certainty there is. Modeling data uncertainty is essential for
regression, especially in unconstrained settings. Traditionally the direct regression …

Combining weight pruning and knowledge distillation for cnn compression

N Aghli, E Ribeiro - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Complex deep convolutional neural networks such as ResNet require expensive hardware
such as powerful GPUs to achieve real-time performance. This problem is critical for …

C3AE: Exploring the limits of compact model for age estimation

C Zhang, S Liu, X Xu, C Zhu - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
Age estimation is a classic learning problem in computer vision. Many larger and deeper
CNNs have been proposed with promising performance, such as AlexNet, VggNet …

Adaptive variance based label distribution learning for facial age estimation

X Wen, B Li, H Guo, Z Liu, G Hu, M Tang… - Computer Vision–ECCV …, 2020 - Springer
Estimating age from a single facial image is a classic and challenging topic in computer
vision. One of its most intractable issues is label ambiguity, ie, face images from adjacent …

FDN: Feature decoupling network for head pose estimation

H Zhang, M Wang, Y Liu, Y Yuan - … of the AAAI conference on artificial …, 2020 - ojs.aaai.org
Head pose estimation from RGB images without depth information is a challenging task due
to the loss of spatial information as well as large head pose variations in the wild. The …

Face image age estimation based on data augmentation and lightweight convolutional neural network

X Liu, Y Zou, H Kuang, X Ma - Symmetry, 2020 - mdpi.com
Face images contain many important biological characteristics. The research directions of
face images mainly include face age estimation, gender judgment, and facial expression …

AttM-CNN: Attention and metric learning based CNN for pornography, age and Child Sexual Abuse (CSA) Detection in images

A Gangwar, V González-Castro, E Alegre, E Fidalgo - Neurocomputing, 2021 - Elsevier
Nowadays, the growing number of cases of possession and distribution of Child Sexual
Abuse (CSA) material pose a significant challenge for Law Enforcement Agencies (LEAs). In …