用于个性化视频注视估计的时空注意力与高斯过程
Spatio-Temporal Attention and Gaussian Processes for Personalized Video Gaze Estimation.
作者信息
Jindal Swati, Yadav Mohit, Manduchi Roberto
机构信息
University of California Santa Cruz.
University of Massachusetts Amherst.
出版信息
Conf Comput Vis Pattern Recognit Workshops. 2024 Jun;2024:604-614. doi: 10.1109/cvprw63382.2024.00065. Epub 2024 Sep 27.
Abstract
2.5° 0.8°. https://github.com/jswati31/stage.
摘要
2.5度 0.8度。https://github.com/jswati31/stage.
相似文献
1
Spatio-Temporal Attention and Gaussian Processes for Personalized Video Gaze Estimation.用于个性化视频注视估计的时空注意力与高斯过程
Conf Comput Vis Pattern Recognit Workshops. 2024 Jun;2024:604-614. doi: 10.1109/cvprw63382.2024.00065. Epub 2024 Sep 27.
2
Contrastive Representation Learning for Gaze Estimation.用于注视估计的对比表示学习
Proc Mach Learn Res. 2023;210:37-49.
3
DSTAN: A Deformable Spatial-temporal Attention Network with Bidirectional Sequence Feature Refinement for Speckle Noise Removal in Thyroid Ultrasound Video.DSTAN：一种具有双向序列特征细化的可变形时空注意力网络，用于去除甲状腺超声视频中的斑点噪声。
J Imaging Inform Med. 2024 Dec;37(6):3264-3281. doi: 10.1007/s10278-023-00935-5. Epub 2024 Jun 5.
4
Spherical DNNs and Their Applications in 360 Images and Videos.球形 DNN 及其在 360 度图像和视频中的应用。
IEEE Trans Pattern Anal Mach Intell. 2022 Oct;44(10):7235-7252. doi: 10.1109/TPAMI.2021.3100259. Epub 2022 Sep 14.
5
In the Eye of the Beholder: Gaze and Actions in First Person Video.旁观者眼中：第一人称视频中的注视与动作
IEEE Trans Pattern Anal Mach Intell. 2023 Jun;45(6):6731-6747. doi: 10.1109/TPAMI.2021.3051319. Epub 2023 May 8.
6
FreeGaze: A Framework for 3D Gaze Estimation Using Appearance Cues from a Facial Video.FreeGaze：一种基于面部视频外观线索的 3D 注视估计框架。
Sensors (Basel). 2023 Dec 4;23(23):9604. doi: 10.3390/s23239604.
7
Appearance-Based Gaze Estimation for ASD Diagnosis.基于外观的孤独症谱系障碍诊断中的注视估计。
IEEE Trans Cybern. 2022 Jul;52(7):6504-6517. doi: 10.1109/TCYB.2022.3165063. Epub 2022 Jul 4.
8
Video action recognition collaborative learning with dynamics via PSO-ConvNet Transformer.基于粒子群优化卷积神经网络变压器的带动力学的视频动作识别协同学习
Sci Rep. 2023 Sep 5;13(1):14624. doi: 10.1038/s41598-023-39744-9.
9
Uncertainty-Aware Gaze Tracking for Assisted Living Environments.用于辅助生活环境的不确定感知注视跟踪。
IEEE Trans Image Process. 2023;32:2335-2347. doi: 10.1109/TIP.2023.3253253. Epub 2023 Apr 21.
10
A self-supervised spatio-temporal attention network for video-based 3D infant pose estimation.基于视频的 3D 婴儿姿态估计的自监督时空注意网络。
Med Image Anal. 2024 Aug;96:103208. doi: 10.1016/j.media.2024.103208. Epub 2024 May 18.
引用本文的文献
1
Gaze Estimation Network Based on Multi-Head Attention, Fusion, and Interaction.基于多头注意力、融合与交互的注视估计网络
Sensors (Basel). 2025 Mar 18;25(6):1893. doi: 10.3390/s25061893.
本文引用的文献
1
Contrastive Representation Learning for Gaze Estimation.用于注视估计的对比表示学习
Proc Mach Learn Res. 2023;210:37-49.
2
Gaze Estimation by Exploring Two-Eye Asymmetry.通过探索双眼不对称性进行注视估计
IEEE Trans Image Process. 2020 Mar 30. doi: 10.1109/TIP.2020.2982828.
3
Multiview Multitask Gaze Estimation With Deep Convolutional Neural Networks.基于深度卷积神经网络的多视图多任务注视估计。
IEEE Trans Neural Netw Learn Syst. 2019 Oct;30(10):3010-3023. doi: 10.1109/TNNLS.2018.2865525. Epub 2018 Sep 3.
4
Temporal Segment Networks for Action Recognition in Videos.用于视频动作识别的时态片段网络
IEEE Trans Pattern Anal Mach Intell. 2019 Nov;41(11):2740-2755. doi: 10.1109/TPAMI.2018.2868668. Epub 2018 Sep 3.
5
Optimizing virtual reality for all users through gaze-contingent and adaptive focus displays.通过注视相关和自适应聚焦显示为所有用户优化虚拟现实。
Proc Natl Acad Sci U S A. 2017 Feb 28;114(9):2183-2188. doi: 10.1073/pnas.1617251114. Epub 2017 Feb 13.
6
Augmented saliency model using automatic 3D head pose detection and learned gaze following in natural scenes.在自然场景中使用自动3D头部姿态检测和学习到的注视跟踪的增强显著性模型。
Vision Res. 2015 Nov;116(Pt B):113-26. doi: 10.1016/j.visres.2014.10.027. Epub 2014 Nov 13.
7
3D convolutional neural networks for human action recognition.三维卷积神经网络的人体动作识别。
IEEE Trans Pattern Anal Mach Intell. 2013 Jan;35(1):221-31. doi: 10.1109/TPAMI.2012.59.
8
Combining head pose and eye location information for gaze estimation.结合头部姿势和眼睛位置信息进行注视估计。
IEEE Trans Image Process. 2012 Feb;21(2):802-15. doi: 10.1109/TIP.2011.2162740. Epub 2011 Jul 22.
9
In the eye of the beholder: a survey of models for eyes and gaze.在观察者的眼中：眼睛和注视模型的调查。
IEEE Trans Pattern Anal Mach Intell. 2010 Mar;32(3):478-500. doi: 10.1109/TPAMI.2009.30.
10
General theory of remote gaze estimation using the pupil center and corneal reflections.利用瞳孔中心和角膜反射进行远程注视估计的一般理论。
IEEE Trans Biomed Eng. 2006 Jun;53(6):1124-33. doi: 10.1109/TBME.2005.863952.
Zotero 插件