https://scholars.lib.ntu.edu.tw/handle/123456789/637404
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | Ashesh | en_US |
dc.contributor.author | CHU-SONG CHEN | en_US |
dc.contributor.author | HSUAN-TIEN LIN | en_US |
dc.date.accessioned | 2023-11-29T01:51:48Z | - |
dc.date.available | 2023-11-29T01:51:48Z | - |
dc.date.issued | 2021-01-01 | - |
dc.identifier.uri | https://scholars.lib.ntu.edu.tw/handle/123456789/637404 | - |
dc.description.abstract | Gaze estimation involves predicting where the person is looking at within an image or video. Technically, the gaze information can be inferred from two different magnification levels: face orientation and eye orientation. The inference is not always feasible for gaze estimation in the wild, given the lack of clear eye patches in conditions like extreme left/right gazes or occlusions. In this work, we design a model that mimics humans' ability to estimate the gaze by aggregating from focused looks, each at a different magnification level of the face area. The model avoids the need to extract clear eye patches and at the same time addresses another important issue of face-scale variation for gaze estimation in the wild. We further extend the model to handle the challenging task of 360-degree gaze estimation by encoding the backward gazes in the polar representation along with a robust averaging scheme. Experiment results on the ETH-XGaze dataset, which does not contain scale-varying faces, demonstrate the model's effectiveness to assimilate information from multiple scales. For other benchmark datasets with many scale-varying faces (Gaze360 and RT-GENE), the proposed model achieves state-of-the-art performance for gaze estimation when using either images or videos. Our code and pretrained models can be accessed at https://github.com/ashesh-0/MultiZoomGaze. | en_US |
dc.relation.ispartof | 32nd British Machine Vision Conference, BMVC 2021 | en_US |
dc.title | 360-Degree Gaze Estimation in the Wild Using Multiple Zoom Scales | en_US |
dc.type | conference paper | en_US |
dc.identifier.scopus | 2-s2.0-85176127621 | - |
dc.identifier.url | https://api.elsevier.com/content/abstract/scopus_id/85176127621 | - |
item.fulltext | no fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_5794 | - |
item.cerifentitytype | Publications | - |
item.openairetype | conference paper | - |
item.grantfulltext | none | - |
crisitem.author.dept | Computer Science and Information Engineering | - |
crisitem.author.dept | Networking and Multimedia | - |
crisitem.author.dept | Computer Science and Information Engineering | - |
crisitem.author.orcid | 0000-0002-2959-2471 | - |
crisitem.author.orcid | 0000-0003-2968-0671 | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。