arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.04464cs.CV
收藏

在Transformer的眼中:用于自我中心视线估计的全局-局部相关性

In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation

Georgia Institute of Technology(佐治亚理工学院)

Bolin Lai, Miao Liu, Fiona Ryan, James M. Rehg

AI总结:

本文提出首个基于transformer的自我中心视线估计模型,通过设计GLC模块显式建模全局上下文token与局部token间的相关性,在EGTEA Gaze+和Ego4D数据集上大幅超越现有方法。

摘要:

本文提出了首个基于transformer的模型来解决自我中心视线估计这一具有挑战性的问题。我们观察到全局场景上下文与局部视觉信息之间的联系对于从自我中心视频帧中定位视线注视点至关重要。为此,我们设计transformer编码器将全局上下文嵌入为一个额外的视觉token,并进一步提出一种新颖的全局-局部相关性(GLC)模块,以显式建模全局token与每个局部token之间的相关性。我们在两个自我中心视频数据集——EGTEA Gaze+和Ego4D上验证了我们的模型。详细的消融实验证明了我们方法的优势。此外,我们的方法大幅超越了先前最先进的方法。我们还提供了额外的可视化结果,以支持我们关于全局-局部相关性作为从自我中心视频中预测视线注视点的关键表示的论断。更多细节可在我们的网站(https://bolinlai.github.io/GLC-EgoGazeEst)找到。

英文摘要:

In this paper, we present the first transformer-based model to address the challenging problem of egocentric gaze estimation. We observe that the connection between the global scene context and local visual information is vital for localizing the gaze fixation from egocentric video frames. To this end, we design the transformer encoder to embed the global context as one additional visual token and further propose a novel Global-Local Correlation (GLC) module to explicitly model the correlation of the global token and each local token. We validate our model on two egocentric video datasets - EGTEA Gaze+ and Ego4D. Our detailed ablation studies demonstrate the benefits of our method. In addition, our approach exceeds previous state-of-the-arts by a large margin. We also provide additional visualizations to support our claim that global-local correlation serves a key representation for predicting gaze fixation from egocentric videos. More details can be found in our website (https://bolinlai.github.io/GLC-EgoGazeEst).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑