Filters








1,254 Hits in 7.1 sec

Deep eye fixation map learning for calibration-free eye gaze tracking

Kang Wang, Shen Wang, Qiang Ji
2016 Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications - ETRA '16  
Furthermore, instead of using saliency map to approximate eye fixation distribution, we propose to use a regression based deep convolutional neural network (RCNN) that specifically learns image features  ...  We apply the proposed method to both 2D regression-based and 3D model-based eye gaze tracking methods.  ...  the distribution based calibration with the deep fixation map to perform implicit eye personal calibration and apply the method to two main approaches for eye gaze tracking.  ... 
doi:10.1145/2857491.2857515 dblp:conf/etra/WangWJ16 fatcat:257zpyd66vci5ccwgdntcfiyua

When I Look into Your Eyes: A Survey on Computer Vision Contributions for Human Gaze Estimation and Tracking

Dario Cazzato, Marco Leo, Cosimo Distante, Holger Voos
2020 Sensors  
revolutionized the whole machine learning area, and gaze tracking as well.  ...  as gaze tracking.  ...  With advances in deep learning, new saliency-based gaze tracking models are continuously proposed, but they are most exploited to learn salient regions in order to predict eye fixations and then eliminate  ... 
doi:10.3390/s20133739 pmid:32635375 pmcid:PMC7374327 fatcat:jwou6gv4f5dy7lrsxvtbnb2fly

Convolutional Neural Network-based Methods for Eye Gaze Estimation: A Survey

Andronicus A. Akinyelu, Pieter Blignaut
2020 IEEE Access  
The recent success and prevalence of deep learning have greatly improved the performance of eye-tracking.  ...  Different methods have been used to tackle eye tracking, however, some of them are inaccurate under real-world conditions, while some require explicit user calibration which can be burdensome.  ...  Hence, recent eye-tracking studies are focusing on developing deep learning-based eye-tracking techniques that do not require explicit user calibration [1] .  ... 
doi:10.1109/access.2020.3013540 fatcat:ezugbll7ivbgrppocfkh7xrcr4

Machine learning accurately classifies age of toddlers based on eye tracking

Kirsten A. Dalrymple, Ming Jiang, Qi Zhao, Jed T. Elison
2019 Scientific Reports  
In contrast, we adopted a data-driven approach by using machine learning (Support Vector Machine (SVM) and Deep Learning (DL)) to elucidate factors that contribute to age-related variability in gaze patterns  ...  This sensitivity for detecting differences in exploratory gaze behavior in toddlers highlights the utility of machine learning for characterizing a variety of developmental capacities.  ...  Given that differences exist between the two groups of gaze patterns, our next exploration uses Deep Learning (DL) to automatically learn and visualize the hierarchical features from the images and eye-tracking  ... 
doi:10.1038/s41598-019-42764-z pmid:31000762 pmcid:PMC6472500 fatcat:o5i2axuom5e3naybl3tnlmz3oa

Creation and validation of a chest X-ray dataset with eye-tracking and report dictation for AI development

Alexandros Karargyris, Satyananda Kashyap, Ismini Lourentzou, Joy T. Wu, Arjun Sharma, Matthew Tong, Shafiq Abedin, David Beymer, Vandana Mukherjee, Elizabeth A. Krupinski, Mehdi Moradi
2021 Scientific Data  
We report deep learning experiments that utilize the attention maps produced by the eye gaze dataset to show the potential utility of this dataset.  ...  The data were collected using an eye-tracking system while a radiologist reviewed and reported on 1,083 CXR images.  ...  for radiology applications and we demonstrate its use in some popular deep learning architectures.  ... 
doi:10.1038/s41597-021-00863-5 pmid:33767191 fatcat:5ilyo5cngffzth46lgc5ypj56i

Creation and Validation of a Chest X-Ray Dataset with Eye-tracking and Report Dictation for AI Development [article]

Alexandros Karargyris, Satyananda Kashyap, Ismini Lourentzou, Joy Wu, Arjun Sharma, Matthew Tong, Shafiq Abedin, David Beymer, Vandana Mukherjee, Elizabeth A Krupinski, Mehdi Moradi
2020 arXiv   pre-print
We report deep learning experiments that utilize the attention maps produced by eye gaze dataset to show the potential utility of this data.  ...  The data were collected using an eye tracking system while a radiologist reviewed and reported on 1,083 CXR images.  ...  for radiology applications and we demonstrate its use in some popular deep learning architectures.  ... 
arXiv:2009.07386v3 fatcat:br6qkfve6vdtzgmlviklucytmi

Invariance Analysis of Saliency Models versus Human Gaze During Scene Free Viewing [article]

Zhaohui Che, Ali Borji, Guangtao Zhai, Xiongkuo Min
2018 arXiv   pre-print
Experimental results verify that some useful data augmentation transformations which preserve human gaze of reference images can improve deep saliency models against distortions, while some invalid transformations  ...  which severely change human gaze will degrade the performance.  ...  We will share our collected data and code with the community to promote research in improving the robustness of deep models over different distortions and to close the gap between saliency models and the  ... 
arXiv:1810.04456v1 fatcat:gurkaxdf7vbrtmj5k3m5z2evzi

Convolutional Neural Network Implementation for Eye-Gaze Estimation on Low-Quality Consumer Imaging Systems

Joseph Lemley, Anuradha Kar, Alexandru Drimbarean, Peter Corcoran
2019 IEEE transactions on consumer electronics  
Accurate and efficient eye gaze estimation is important for emerging consumer electronic systems such as driver monitoring systems and novel user interfaces.  ...  The model is tested and compared against existing appearance based CNN approaches, achieving better eye gaze accuracy with significantly fewer computational requirements.  ...  Deep Learning for Eye Gaze In this paper, we introduce a calibration-free method for appearance-based gaze estimation that is suitable for consumer applications and low cost hardware with real time requirements  ... 
doi:10.1109/tce.2019.2899869 fatcat:mker4tuvujevdackzb2m6ubgu4

Remote Eye Gaze Tracking Research: A Comparative Evaluation on Past and Recent Progress

Ibrahim Shehi Shehu, Yafei Wang, Athuman Mohamed Athuman, Xianping Fu
2021 Electronics  
Eye gaze data in a broad sense has been used in research and systems for eye movements, eye tracking, and eye gaze tracking.  ...  Since early 2000, eye gaze tracking systems have emerged as interactive gaze-based systems that could be remotely deployed and operated, known as remote eye gaze tracking (REGT) systems.  ...  Handheld, 1 web camera CNN, Calibration free appearance-based [191] 81.37% Desktop, 1 web camera CNN, Calibration free with deep learning [17] 1.71 cm and 2.53 cm Handheld, 1web camera CNN, Calibration  ... 
doi:10.3390/electronics10243165 fatcat:ju3gsvvlezcvxplda6f5aabb74

Efficient CNN Implementation for Eye-Gaze Estimation on Low-Power/Low-Quality Consumer Imaging Systems [article]

Joseph Lemley, Anuradha Kar, Alexandru Drimbarean, Peter Corcoran
2018 arXiv   pre-print
Accurate and efficient eye gaze estimation is important for emerging consumer electronic systems such as driver monitoring systems and novel user interfaces.  ...  The model is tested and compared against existing appearance based CNN approaches, achieving better eye gaze accuracy with significantly fewer computational requirements.  ...  Project ID: 13/SPP/I2868 on Next Generation Imaging for Smartphone and Embedded Platforms. This work is also supported by an Irish Research Council Employment Based Programme Award.  ... 
arXiv:1806.10890v1 fatcat:cp6k4rx3gzc33morknlhcpw7di

DeepVOG: Open-source Pupil Segmentation and Gaze Estimation in Neuroscience using Deep Learning

Yuk-Hoi Yiu, Moustafa Aboulatta, Theresa Raiser, Leoni Ophey, Virginia L. Flanagin, Peter zu Eulenburg, Seyed-Ahmad Ahmadi
2019 Journal of Neuroscience Methods  
A prerequisite for many eye tracking and video-oculography (VOG) methods is an accurate localization of the pupil.  ...  Instead, we utilize a deep-learning model to autonomously learn the optimal image filters and segmentation rules from training data.  ...  For 3D eye model fitting using our framework, each subject additionally performed two projector-free, unassisted calibrations with three trials each (for details, see Section 2.5).  ... 
doi:10.1016/j.jneumeth.2019.05.016 pmid:31176683 fatcat:h5gi4d6lhbeenmnbbrirgdu3xm

Saliency Prediction for Mobile User Interfaces [article]

Prakhar Gupta, Shubh Gupta, Ajaykrishnan Jayagopal, Sourav Pal, Ritwik Sinha
2017 arXiv   pre-print
We first collected eye-gaze data from mobile devices for free viewing task.  ...  Using this data, we develop a novel autoencoder based multi-scale deep learning model that provides saliency prediction at the mobile interface element level.  ...  For desktop devices, eye-gaze tracking as a form of user engagement feedback has been studied [16] .  ... 
arXiv:1711.03726v3 fatcat:bcrtqg3horckrnnwbipl5n6doa

Predicting the Category and Attributes of Visual Search Targets Using Deep Gaze Pooling

Hosnieh Sattar, Andreas Bulling, Mario Fritz
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
However, state-of-the-art models for categorical recognition require large amounts of training data, which is prohibitive for gaze data.  ...  We show that our approach can leverage pre-trained CNN architectures, thus eliminating the need for expensive joint data collection of image and gaze data.  ...  We also thank Mykhaylo Andriluka for helpful comments on the paper.  ... 
doi:10.1109/iccvw.2017.322 dblp:conf/iccvw/SattarBF17 fatcat:7opkss22bnhxnmwp7cjamwinb4

Automatic Gaze Analysis: A Survey of Deep Learning based Approaches [article]

Shreya Ghosh, Abhinav Dhall, Munawar Hayat, Jarrod Knibbe, Qiang Ji
2022 arXiv   pre-print
Eye gaze analysis is an important research problem in the field of Computer Vision and Human-Computer Interaction.  ...  Even with notable progress in the last 10 years, automatic gaze analysis still remains challenging due to the uniqueness of eye appearance, eye-head interplay, occlusion, image quality, and illumination  ...  Non deep learning methods or early deep learning methods [21] , [24] , [50] , [51] perform these mappings. 2) 3-D Gaze Estimation: The 3-D gaze estimation basically considers the gaze vector instead  ... 
arXiv:2108.05479v3 fatcat:6qhwjojyqbdctjcwnjerflvyzi

EyeTrackUAV2: A Large-Scale Binocular Eye-Tracking Dataset for UAV Videos

Anne-Flore Perrin, Vassilios Krassanakis, Lu Zhang, Vincent Ricordel, Matthieu Perreira Da Silva, Olivier Le Meur
2020 Drones  
To conduct saliency studies, we identified the need for new large-scale eye-tracking datasets for visual salience in UAV content.  ...  Fixations and saccades were then computed with the dispersion-threshold identification (I-DT) algorithm, while gaze density maps were calculated by filtering eye positions with a Gaussian kernel.  ...  The first row presents sequences hundredth frame, the second fixations for free viewing (FV), the third gaze density maps for FV, the fourth fixations for the surveillance-viewing task (called Task), and  ... 
doi:10.3390/drones4010002 fatcat:35fawpqxn5ctdcnoneuxti3bju
« Previous Showing results 1 — 15 out of 1,254 results