Learning a 3D Gaze Estimator With Adaptive Weighted Strategy

Zhou, Xiaolong; Jiang, Jiaqi; Liu, Qianqian; Fang, Jianwen; Chen, Shengyong; Cai, Haibin

doi:10.1109/access.2020.2990685

Cited by 6 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve the generalization performance of appearance-based models, Wang proposed a method combining adversarial learning with Bayesian inference for the overfitting of appearance, head pose, and point estimation [8]. To solve the interference of face images with free head movement on the line of sight model mapping, Zhou proposed to input different areas of the face into the 3D line of sight estimator with adaptive weighting during head movement, which greatly improved the efficiency and accuracy of the regression model [9].…”

Section: A Gaze Estimationmentioning

confidence: 99%

Research on Gaze Estimation Method Combined with Head Motion Changes

Zhan

Wang

2022

International Journal of Advanced Network, Monitoring and Controls

View full text Add to dashboard Cite

The line of sight reflects the focus of human attention. Gaze estimation technology has a wide range of application prospects in human-computer interaction, human emotion analysis, commercial advertising, and so on. Gaze estimation needs to be jointly determined by eye movement and head movement because the human gaze is often with the head movement. In this paper, a gaze estimation system with head movement is implemented by a monocular camera, using eye movement features and head movement posture changes to estimate the gaze point. A camera is used as the information acquisition device to extract the eye movement feature information, and the offset of head movement is estimated at the same time. The final fixation point position coordinates are obtained by compensating the fixation point position in the case of head movement, and then the fixation point position coordinates are estimated. For the compensated gaze drop point, the average pixel error on the X-axis is estimated to be 118 pixels, and the average pixel error on the Y-axis is estimated to be 136 pixels.

show abstract

Section: A Gaze Estimationmentioning

confidence: 99%

Research on Gaze Estimation Method Combined with Head Motion Changes

Zhan

Wang

2022

International Journal of Advanced Network, Monitoring and Controls

View full text Add to dashboard Cite

show abstract

“…More and more complex neural network models are used to accurately determine the gaze angle. In the article [5], the authors propose to consider and submit to the network input 3 images at once, this is the image of each eye and face as a whole. The main idea of the authors is that the weight of each of these three images varies from case to case.…”

Section: Three-dimensional Gaze Angle Recognition Algorithmmentioning

confidence: 99%

Operator’s Gaze Direction Recognition

Popov

Shakhuro

Konushin

2021

Proceedings of the 31th International Conference on Computer Graphics and Vision. Volume 2

View full text Add to dashboard Cite

This work is devoted to the algorithm for recognizing the direction of a operator’s gaze. The paper considers the method of classifying the direction of gaze. The algorithm proposed in this paper allows to determine the driver’s gaze direction, which helps to protect the driving process. In the proposed work, we reviewed the algorithms and methods used to recognize the human gaze in various conditions. For each given method, a list of their positive and negative qualities is indicated. Based on the results of the review, an algorithm for classifying the car driver’s gaze direction is proposed. The proposed algorithm consists of two components. The first part is responsible for the regression of the gaze direction. The second part is responsible for classifying the results of the first part. Experimental evaluation of the developed algorithm has shown that it is effective for the task of classifying the gaze direction. An important advantage of this algorithm is that it does not require repeated training of the algorithm to adapt to other scenarios of gaze direction classification.

show abstract

“…It uses high-level knowledge to filter the distractive information and bridges the intrinsic relationship between face and eye features. Zhou et al [25] proposed a weighted network with an adaptive adjustment regression strategy, which learns the varying contributions of different regions to gaze estimation outcomes under free head movement. And there are some methods incorporate attention mechanisms to enhance the consideration of interrelationships between distinct regions.…”

Section: Cheng Et Al Introduced the Gazetr Modelmentioning

confidence: 99%

Gaze Estimation Based on Attention Mechanism Combined With Temporal Network

Ren,

Zhang,

Feng

2023

IEEE Access

View full text Add to dashboard Cite

Due to the continuous and dynamic nature of gaze estimation, the true gaze point at each moment is closely related to the previous moment. Simply detecting individual frames of facial images cannot yield accurate gaze information. In current CNN-based gaze estimation methods, the effective utilization of eye movement temporal information and the ability to capture global relationships in the feature extraction process remain problematic. Addressing these concerns, this paper proposes a novel gaze estimation framework, named FE-net, which incorporates a temporal network. This framework introduces channel attention modules and self-attention modules, enhancing the comprehensive utilization of extracted features and reinforcing the contribution of valuable regions to gaze estimation. We further integrate an RNN structure to learn the temporal dynamics of eye movement processes, significantly improving gaze direction prediction accuracy. This framework predicts the gaze directions of left and right eyes separately using monocular and facial features and computes the overall gaze direction. FEnet achieves state-of-the-art accuracy of 3.19° and 3.16° on the EVE dataset and the MPIIFaceGaze dataset, respectively.

show abstract

Learning a 3D Gaze Estimator With Adaptive Weighted Strategy

Cited by 6 publications

References 38 publications

Research on Gaze Estimation Method Combined with Head Motion Changes

Research on Gaze Estimation Method Combined with Head Motion Changes

Operator’s Gaze Direction Recognition

Gaze Estimation Based on Attention Mechanism Combined With Temporal Network

Contact Info

Product

Resources

About