Real-time head pose estimation using multi-task deep neural network

Ahn, Byung-Tae; Choi, Dong‐Geol; Park, Jaesik; Kweon, In So

doi:10.1016/j.robot.2018.01.005

Cited by 51 publications

(39 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work mainly focuses on the head pose estimation for robust face recognition [5]. Existing head pose estimation methods can be roughly classified into two categories: modelbased methods [12][13][14] and appearance-based methods [7,8,[15][16][17][18][19][20][21][22][23][24][25][26].…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, appearance-based methods receive much attention recently. These methods depend on pose-invariant local features or the localization of facial feature points [7], which include appearance template methods [8,17], detector array methods [15], nonlinear regression methods [7,[16][17][18][19][20], manifold embedding methods [21][22][23], and Convolutional Neural Network (CNN) based methods [24][25][26].…”

Section: Related Workmentioning

confidence: 99%

“…Later, Patacchiola and Cangelosi [25] developed a head pose estimation method using CNN and adaptive gradient methods to obtain the promising performance. Ahn et al [26] used the multitask deep CNN for real-time head pose estimation. However, most of the CNN based methods suffer from high computational complexity.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Directional Correlation Filter Bank for Robust Head Pose Estimation and Face Recognition

Chen

Yan

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

During the past few decades, face recognition has been an active research area in pattern recognition and computer vision due to its wide range of applications. However, one of the most challenging problems encountered by face recognition is the difficulty of handling large head pose variations. Therefore, the efficient and effective head pose estimation is a critical step of face recognition. In this paper, a novel feature extraction framework, called Directional Correlation Filter Bank (DCFB), is presented for head pose estimation. Specifically, in the proposed framework, the 1-Dimensional Optimal Tradeoff Filters (1D-OTF) corresponding to different head poses are simultaneously and jointly designed in the low-dimensional linear subspace. Different from the traditional methods that heavily rely on the precise localization of the key facial feature points, our proposed framework exploits the frequency domain of the face images, which effectively captures the high-order statistics of faces. As a result, the obtained features are compact and discriminative. Experimental results on public face databases with large head pose variations show the superior performance obtained by the proposed framework on the tasks of both head pose estimation and face recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Directional Correlation Filter Bank for Robust Head Pose Estimation and Face Recognition

Chen

Yan

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…The two most important steps in a convolutional neural network are the pooling and convolution operations. The main function of the pooling operation is to reduce the number of computation parameters, and the convolution operation is used to extract local features [21][22][23]. To adapt the model to the various sizes of input, the model for the well log data is defined as model left, and its parameters are listed in Table 1.…”

Section: Implementation Of the Alexnet-based Modelmentioning

confidence: 99%

A Novel Multi-Input AlexNet Prediction Model for Oil and Gas Production

Wang

Yin

Guo

et al. 2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In the process of oilfield development, it is important to predict the oil and gas production. The predicted value of oil production is the amount of oil that may be obtained within a certain area over a certain period. Because of the current demand for oil and gas production prediction, a prediction model using a multi-input convolutional neural network based on AlexNet is proposed in this paper. The model predicts real oilfield data and achieves good results: increasing prediction accuracy by 17.5%, 20.8%, 11.6%, 8.9%, 6.9%, and 14.9% with respect to the backpropagation neural network, support vector machine, artificial neural network, radial basis function neural network, K-nearest neighbor, and decision tree methods, respectively. It addresses the uncertainty of oil and gas production caused by the change in parameter values during the process of petroleum exploitation and has far-reaching application significance.

show abstract

“…MTL is widely used in a broad range of practical applications, including face detection (Ranjan et al, 2017;Ahn et al, 2018;Chen et al, 2018;Zhao et al, 2019), federated MTL (Smith et al, 2017;Corinzia and Buhmann, 2019;Sattler et al, 2019), speech recognition (Huang et al, 2013;Kim et al, 2017;Liu et al, 2017;Subramanian et al, 2018), and other applications (Doersch and Zisserman, 2017;Han et al, 2017;Liu et al, 2017Liu et al, , 2019Hessel et al, 2019). Ranjan et al (2017) presented an algorithm for simultaneous face detection, landmark localization, pose estimation, and gender recognition.…”

Section: Introductionmentioning

confidence: 99%

A Privacy-Preserving Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

Zhang

Xie

et al. 2020

Front. Neurorobot.

View full text Add to dashboard Cite

Recently, multi-task learning (MTL) has been extensively studied for various face processing tasks, including face detection, landmark localization, pose estimation, and gender recognition. This approach endeavors to train a better model by exploiting the synergy among the related tasks. However, the raw face dataset used for training often contains sensitive and private information, which can be maliciously recovered by carefully analyzing the model and outputs. To address this problem, we propose a novel privacy-preserving multi-task learning approach that utilizes the differential private stochastic gradient descent algorithm to optimize the end-to-end multi-task model and weighs the loss functions of multiple tasks to improve learning efficiency and prediction accuracy. Specifically, calibrated noise is added to the gradient of loss functions to preserve the privacy of the training data during model training. Furthermore, we exploit the homoscedastic uncertainty to balance different learning tasks. The experiments demonstrate that the proposed approach yields differential privacy guarantees without decreasing the accuracy of HyperFace under a desirable privacy budget.

show abstract

Real-time head pose estimation using multi-task deep neural network

Cited by 51 publications

References 33 publications

Directional Correlation Filter Bank for Robust Head Pose Estimation and Face Recognition

Directional Correlation Filter Bank for Robust Head Pose Estimation and Face Recognition

A Novel Multi-Input AlexNet Prediction Model for Oil and Gas Production

A Privacy-Preserving Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

Contact Info

Product

Resources

About