2018
DOI: 10.1016/j.robot.2018.01.005
|View full text |Cite
|
Sign up to set email alerts
|

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

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
39
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 52 publications
(39 citation statements)
references
References 33 publications
0
39
0
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%
See 2 more Smart Citations
“…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%
See 1 more Smart Citation
“…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%
“…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%