An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking

  title={An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking},
  author={Jiahao Xia and Haimin Zhang and Shiping Wen and Shuo Yang and Min Xu},
  journal={Expert Syst. Appl.},

PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimation

We present a multitask network that supports various deep neural network based pedestrian detection functions. Besides 2D and 3D human pose, it also supports body and head orientation estimation

methods Facial Expression Recognition by Regional Attention and Multi-task

A new end-to-end region attention and multitask learning network (RAMN) for FER that learns the importance of the facial features and combines different numbers of regional features obtained from the neural network for Fer.

Fatigue detection based on facial feature correction and fusion

A feature extraction algorithm based on Euler angle correction is proposed, and a multi-feature fusion decision method is added to enhance the applicability of the algorithm.



Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks

A deep cascaded multitask framework that exploits the inherent correlation between detection and alignment to boost up their performance and achieves superior accuracy over the state-of-the-art techniques on the challenging face detection dataset and benchmark.

Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources

The first to study the effect of neural network binarization on localization tasks, namely human pose estimation and face alignment, and proposes a novel hierarchical, parallel and multi-scale residual architecture that yields large performance improvement over the standard bottleneck block while having the same number of parameters.

HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

The proposed method, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features to exploit the synergy among the tasks which boosts up their individual performances.

Improving multiview face detection with multi-task deep convolutional neural networks

A deep convolutional neural network is built that can simultaneously learn the face/nonface decision, the face pose estimation problem, and the facial landmark localization problem and it is shown that such a multi-task learning scheme can further improve the classifier's accuracy.

Fine-Grained Head Pose Estimation Without Keypoints

An elegant and robust way to determine pose is presented by training a multi-loss convolutional neural network on 300W-LP, a large synthetically expanded dataset, to predict intrinsic Euler angles directly from image intensities through joint binned pose classification and regression.

Face Alignment Across Large Poses: A 3D Solution

3D Dense Face Alignment (3DDFA), in which a dense 3D face model is fitted to the image via convolutional neutral network (CNN), is proposed, and a method to synthesize large-scale training samples in profile views to solve the third problem of data labelling is proposed.

Knowing When to Quit: Selective Cascaded Regression with Patch Attention for Real-Time Face Alignment

This work analyses the patch attention data to infer where the model is attending when regressing facial landmarks and compares it to face attention in humans, and offers a multi-scale, patch-based, lightweight feature extractor with a fine-grained local patch attention module, which computes a patch weighting according to the information in the patch itself and enhances the expressive power of the patch features.

A New Dataset and Boundary-Attention Semantic Segmentation for Face Parsing

A simple yet effective Boundary-Attention Semantic Segmentation (BASS) method is proposed for face parsing, which contains a three-branch network with elaborately developed loss functions to fully exploit the boundary information.

Leveraging Intra and Inter-Dataset Variations for Robust Face Alignment

  • Wenyan WuShuo Yang
  • Computer Science
    2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2017
A novel Deep Variation Leveraging Network (DVLN) is proposed, which consists of two strong coupling sub-networks, e.g., Dataset-Across Network (DA-Net) and Candidate-Decision Network (CD-Net), which takes advantage of different characteristics and distributions across different datasets, while CD-Net makes a final decision on candidate hypotheses given by DA-Net to leverage variations within one certain dataset.