Sep 11, 2019 · Both streams are seamlessly integrated via a fusion network. Extensive experiments are performed on a fully annotated group gaze image dataset ...

The MUGGLE infrastructure includes two inference streams: 1) a holistic stream which utilizes fused attention map as input to a global deep convolutional ...

The results demonstrate the effectiveness of the proposed MUGGLE framework in group gaze estimation and demonstrate the importance of knowing the common ...

Connected Papers is a visual tool to help researchers and applied scientists find academic papers relevant to their field of work.

MUGGLE: MUlti-stream group gaze learning and estimation. N Zhuang, B Ni, Y Xu, X Yang, W Zhang, Z Li, W Gao. IEEE Transactions on Circuits and Systems for Video ...

Oct 22, 2024 · ... Multi-stream Group Gaze Learning and Estimation (MUGGLE). The MUGGLE infrastructure includes two inference streams: 1) a holistic stream ...

Gaze target detection aims to infer where each person in a scene is looking. Existing works focus on 2D gaze and. 2D saliency, but fail to exploit 3D ...

This paper addresses the gaze target detection problem in single images captured from the third-person perspective.

... Multi-stream Group Gaze Learning and Estimation (MUGGLE). The MUGGLE infrastructure includes two inference streams: 1) a holistic stream which utilizes ...

MUGGLE: MUlti-Stream Group Gaze Learning and Estimation. IEEE Trans. Circuits Syst. Video Technol. 30(10): 3637-3650 (2020). [+][–]. 2010 – 2019. FAQ. see FAQ.