EVA-GCN: Head Pose Estimation Based on Graph Convolutional Networks

Miao, Xin; Mo, Shentong; Lin, Yuanze

doi:10.1109/cvprw53098.2021.00162

Cited by 26 publications

(16 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our proposed network with other stateof-the-art head pose estimation methods on BIWI and AFLW datasets. KEPLER (Kumar et al, 2017), FAN (Bulat and Tzimiropoulos, 2017), Dlib (Kazemi and Sullivan, 2014) and EVA-GCN (Xin et al, 2021) are landmark-based methods. KEPLER (Kumar et al, 2017) uses a modified GoogleNet to pre- (Kazemi and Sullivan, 2014) is a face library that uses an ensemble of regression trees to detect landmarks.…”

Section: Resultsmentioning

confidence: 99%

“…FAN (Bulat and Tzimiropoulos, 2017) is a state-of-the-art landmark detection method. EVA-GCN (Xin et al, 2021) is a stateof-the-art landmark-based method which constructs a landmark-connection graph and leverages the Graph Convolution Network (Yan et al, 2018) to learn the nonlinear relationships between head poses and distribution of facial keypoints. HopeNet (Ruiz et al, 2018), FSANet (Yang et al, 2019) and WHENet (Zhou and Gregson, 2020) are landmark free methods which treat the regression problem as classification problem by dividing the poses range to different classes.…”

Section: Resultsmentioning

confidence: 99%

“…FAN (Bulat and Tzimiropoulos, 2017) using deep neural network to estimate 3D face models. EVA-GCN (Xin et al, 2021) constructs a landmarkconnection graph and leverages the Graph Convolution Network (Yan et al, 2018) to learn the nonlinear relationships between head poses and distribution of facial keypoints.…”

Section: Related Workmentioning

confidence: 99%

“…The objective of head pose estimation is to accurately identify the orientation of heads of individuals found in images. Existing methods to solve this problem can be divided into two primary categories: landmark-based approaches (Cao et al, 2014;Lathuilière et al, 2017;Fanelli et al, 2011;Xiong and De la Torre, 2015;Sun et al, 2013;Xin et al, 2021;Bulat and Tzimiropoulos, 2017;DeMenthon and Davis, 1995) and landmark-free approach (Ruiz et al, 2018;Yang et al, 2019;Zhou and Gregson, 2020;Chang et al, 2017). Landmark-based methods use facial keypoints extracted by landmark detectors to regress the head pose angle.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Effective Deep Network for Head Pose Estimation without Keypoints

Thai¹,

Tran²,

Bui³

et al. 2022

Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

Human head pose estimation is an essential problem in facial analysis in recent years that has a lot of computer vision applications such as gaze estimation, virtual reality, driver assistance. Because of the importance of the head pose estimation problem, it is necessary to design a compact model to resolve this task in order to reduce the computational cost when deploying on facial analysis-based applications such as large camera surveillance systems, AI cameras while maintaining accuracy. In this work, we propose a lightweight model that effectively addresses the head pose estimation problem. Our approach has two main steps. 1) We first train many teacher models on the synthesis dataset -300W-LPA to get the head pose pseudo labels. 2) We design an architecture with the ResNet18 backbone and train our proposed model with the ensemble of these pseudo labels via the knowledge distillation process. To evaluate the effectiveness of our model, we use AFLW-2000 and BIWItwo real-world head pose datasets. Experimental results show that our proposed model significantly improves the accuracy in comparison with the state-of-the-art head pose estimation methods. Furthermore, our model has the real-time speed of ∼300 FPS when inferring on Tesla V100.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Effective Deep Network for Head Pose Estimation without Keypoints

Thai¹,

Tran²,

Bui³

et al. 2022

Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

show abstract

“…A. Kumar et al [12] used modified GoogleNet and adopt multi-task learning to jointly learn facial landmarks and pose. Recent work, Xin et al [13] used Graph Convolution Network (GCN) for direct regression of the 3D head pose, which considered a landmark-connection graph based on k-Nearest Neighbor relations. Specifically, this work also introduced many modules such as joint Edge-Vertex Attention (EVA), Adaptive Channel Attention (ACA) and Densely-Connected Architecture (DCA) to further boost the performance.…”

Section: Landmark-basedmentioning

confidence: 99%

3D Head Pose Estimation Based on Graph Convolutional Network from A Single RGB Image

Lie

Yim

Aing

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Research of head pose estimation in computer vision has been at the center of much attention. This work presents a framework based on adaptive graph convolution network (AGCN) to process both 2D and 3D facial landmarks extracted from the input RGB image. The network has a two-streams (teacher/3D-student/2D streams) architecture, trained with a 3D to 2D knowledge distillation training process, to transfer features of the 3D stream to the 2D stream for performance promotion. Several processing modules, such as depth-denoising for detected 3D landmarks, multi-stream fusion in inference, were also proposed for further increase of the prediction performance and robustness of our proposed method. In experiments, we follow standard protocols (in terms of datasets and metrices) to evaluate our performance. Three datasets 300W-LP, AFLW2000 and BIWI were used. The performance is measured in mean absolute error (MAE). We can achieve better performance compared to most of the state-of-theart methods.

show abstract