MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation

Zhang, Xucong; Sugano, Yusuke; Fritz, Mario; Bulling, Andreas

doi:10.1109/tpami.2017.2778103

Cited by 383 publications

(414 citation statements)

References 65 publications

Supporting

Mentioning

407

Contrasting

Order By: Relevance

“…However, person-independent gaze errors are still insufficient for many applications [3,43,19,2]. While significant gains can be obtained by training person-specific models, it requires many thousands of training images per subject [58]. On the other hand, CNNs are prone to over-fitting if trained with very few (k ≤ 9) samples.…”

Section: Related Workmentioning

confidence: 99%

Few-Shot Adaptive Gaze Estimation

Park

Mello²,

Molchanov³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

167

128

View full text Add to dashboard Cite

Inter-personal anatomical differences limit the accuracy of person-independent gaze estimation networks. Yet there is a need to lower gaze errors further to enable applications requiring higher quality. Further gains can be achieved by personalizing gaze networks, ideally with few calibration samples. However, over-parameterized neural networks are not amenable to learning from few examples as they can quickly over-fit. We embrace these challenges and propose a novel framework for Few-shot Adaptive GaZE Estimation (FAZE) for learning person-specific gaze networks with very few (≤ 9) calibration samples. FAZE learns a rotation-aware latent representation of gaze via a disentangling encoder-decoder architecture along with a highly adaptable gaze estimator trained using meta-learning. It is capable of adapting to any new person to yield significant performance gains with as few as 3 samples, yielding state-of-the-art performance of 3.18 • on GazeCapture, a 19% improvement over prior art.

show abstract

Section: Related Workmentioning

confidence: 99%

Few-Shot Adaptive Gaze Estimation

Park

Mello²,

Molchanov³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

167

128

View full text Add to dashboard Cite

show abstract

“…Even at 90 − 135 • head yaw a significant part of one eyeball is often still visible and informative for gaze estimation (see Supplemental). Existing methods [12,32] do not deal with these cases and typically assume that the subject is facing the camera. However, such models do not generalize well to challenging applications such as in robotics or surveillance.…”

Section: Related Workmentioning

confidence: 99%

Gaze360: Physically Unconstrained Gaze Estimation in the Wild

Kellnhofer

Recasens

Stent³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

265

254

View full text Add to dashboard Cite

Understanding where people are looking is an informative social cue. In this work, we present Gaze360, a large-scale gaze-tracking dataset and method for robust 3D gaze estimation in unconstrained images. Our dataset consists of 238 subjects in indoor and outdoor environments with labelled 3D gaze across a wide range of head poses and distances. It is the largest publicly available dataset of its kind by both subject and variety, made possible by a simple and efficient collection method. Our proposed 3D gaze model extends existing models to include temporal information and to directly output an estimate of gaze uncertainty. We demonstrate the benefits of our model via an ablation study, and show its generalization performance via a cross-dataset evaluation against other recent gaze benchmark datasets. We furthermore propose a simple self-supervised approach to improve cross-dataset domain adaptation. Finally, we demonstrate an application of our model for estimating customer attention in a supermarket setting. Our dataset and models are available at

show abstract

“…Generic gaze estimator. As our gaze estimator, we use GazeNet [45]. It is is based on a vgg16 architecture.…”

Section: Experimental Settingmentioning

confidence: 99%

Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis

Liu

Odobez

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

As an indicator of human attention gaze is a subtle behavioral cue which can be exploited in many applications. However, inferring 3D gaze direction is challenging even for deep neural networks given the lack of large amount of data (groundtruthing gaze is expensive and existing datasets use different setups) and the inherent presence of gaze biases due to person-specific difference. In this work, we address the problem of person-specific gaze model adaptation from only a few reference training samples. The main and novel idea is to improve gaze adaptation by generating additional training samples through the synthesis of gaze-redirected eye images from existing reference samples. In doing so, our contributions are threefold: (i) we design our gaze redirection framework from synthetic data, allowing us to benefit from aligned training sample pairs to predict accurate inverse mapping fields; (ii) we proposed a self-supervised approach for domain adaptation; (iii) we exploit the gaze redirection to improve the performance of person-specific gaze estimation. Extensive experiments on two public datasets demonstrate the validity of our gaze retargeting and gaze estimation framework.

show abstract

MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation

Cited by 383 publications

References 65 publications

Few-Shot Adaptive Gaze Estimation

Few-Shot Adaptive Gaze Estimation

Gaze360: Physically Unconstrained Gaze Estimation in the Wild

Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis

Contact Info

Product

Resources

About