中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
Unsupervised Gaze Representation Learning by Switching Features

文献类型：期刊论文

作者Sun, Yunjia1,3; Zeng, Jiabei1,2; Shan, Shiguang1,2; Chen, Xilin1,2
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2026
卷号48期号:1页码:62-78
关键词Estimation Faces Three-dimensional displays Switches Training Feature extraction Cameras Representation learning Convolutional neural networks Unsupervised learning Gaze estimation unsupervised learning self-supervised learning representation learning feature disentanglement
ISSN号0162-8828
DOI10.1109/TPAMI.2025.3600680
英文摘要It is prevalent to leverage unlabeled data to train deep learning models when it is difficult to collect large-scale annotated datasets. However, for 3D gaze estimation, most existing unsupervised learning methods face challenges in distinguishing subtle gaze-relevant information from dominant gaze-irrelevant information. To address this issue, we propose an unsupervised learning framework to disentangle the gaze-relevant and the gaze-irrelevant information, by seeking the shared information of a pair of input images with the same gaze and with the same eye respectively. Specifically, given two images, the framework finds their shared information by first encoding the images into two latent features via two encoders and then switching part of the features before feeding them to the decoders for image reconstruction. We theoretically prove that the proposed framework is able to encode different information into different parts of the latent feature if we properly select the training image pairs and their shared information. Based on the framework, we derive Cross-Encoder and Cross-Encoder++ to learn gaze representation from the eye images and face images, respectively. Experiments on public gaze datasets demonstrate that the Cross-Encoder and Cross-Encoder++ outperform the competitive methods. The ablation study quantitatively and qualitatively shows that the gaze feature is successfully extracted.
资助项目National Natural Science Foundation of China[U2336213] ; National Natural Science Foundation of China[62176248]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001630351400036
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/42805]  
专题中国科学院计算技术研究所
通讯作者Zeng, Jiabei
作者单位1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Peking Univ, Beijing 100871, Peoples R China
推荐引用方式
GB/T 7714		 Sun, Yunjia,Zeng, Jiabei,Shan, Shiguang,et al. Unsupervised Gaze Representation Learning by Switching Features[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2026,48(1):62-78.
APA Sun, Yunjia,Zeng, Jiabei,Shan, Shiguang,&Chen, Xilin.(2026).Unsupervised Gaze Representation Learning by Switching Features.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,48(1),62-78.
MLA Sun, Yunjia,et al."Unsupervised Gaze Representation Learning by Switching Features".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 48.1(2026):62-78.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。