Skip to content
JournalsWorldThe Global Research Discovery Platform
Login Sign Up
SCHOLARLY PUBLICATION ✓ Open Access

It’s Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation

Xucong Zhang, Yusuke Sugano, Mario Fritz, Andreas Bulling

📖 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 📅 2017-07-01 🔗 DOI: 10.1109/cvprw.2017.284
⬇ Download PDF View Official Paper ↗

📄 Abstract

Eye gaze is an important non-verbal cue for human affect analysis. Recent gaze estimation work indicated that information from the full face region can benefit performance. Pushing this idea further, we propose an appearance-based method that, in contrast to a long-standing line of work in computer vision, only takes the full face image as input. Our method encodes the face image using a convolutional neural network with spatial weights applied on the feature maps to flexibly suppress or enhance information in different facial regions. Through extensive evaluation, we show that our full-face method significantly outperforms the state of the art for both 2D and 3D gaze estimation, achieving improvements of up to 14.3% on MPIIGaze and 27.7% on EYEDIAP for person-independent 3D gaze estimation. We further show that this improvement is consistent across different illumination conditions and gaze directions and particularly pronounced for the most challenging extreme head poses.

📤 Share this page

Found this useful? Share it with your network.

𝕏XfFacebookinLinkedIn✆WhatsApp✈Telegram✉EmailMMendeley
✓ Link copied! Paste it on ResearchGate / Academia.edu

🔬 Related Research Papers

IEEE Conference on Computer Vision and P

Intel(R) RealSense(TM) Stereoscopic Depth Cameras

Leonid Keselman, J. Woodfill et al. 2017-07-01 · Read paper → IEEE Conference on Computer Vision and P

Streetscore -- Predicting the Perceived Safety of One Million Streetscapes

Nikhil Naik, Jade Philipoom et al. 2014-06-01 · Read paper → IEEE Conference on Computer Vision and P

Hand gesture recognition with 3D convolutional neural networks

Pavlo A. Molchanov, Shalini Gupta et al. 2015-06-01 · Read paper → IEEE Conference on Computer Vision and P

SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

Bichen Wu, Alvin Wan et al. 2017-07-01 · Read paper → IEEE Conference on Computer Vision and P

Semantic Segmentation of Small Objects and Modeling of Uncertainty in Urban Remote Sensing Images Using Deep Convolutional Neural Networks

Michael Kampffmeyer, Arnt-Børre Salberg, Robert Jenssen 2016-06-01 · Read paper → IEEE Conference on Computer Vision and P

Deep learning of binary hash codes for fast image retrieval

Kevin Lin, Huei‐Fang Yang et al. 2015-06-01 · Read paper → IEEE Conference on Computer Vision and P

Two-Stream Neural Networks for Tampered Face Detection

Peng Zhou, Xintong Han et al. 2017-07-01 · Read paper → IEEE Conference on Computer Vision and P

Do deep features generalize from everyday objects to remote sensing and aerial scenes domains?

Otávio A. B. Penatti, Keiller Nogueira, Jefersson A. dos Santos 2015-06-01 · Read paper → IEEE Conference on Computer Vision and P

Interpretable 3D Human Action Analysis with Temporal Convolutional Networks

Tae Soo Kim, Austin Reiter 2017-07-01 · Read paper → IEEE Conference on Computer Vision and P

AgeDB: The First Manually Collected, In-the-Wild Age Database

Stylianos Moschoglou, Athanasios Papaioannou et al. 2017-07-01 · Read paper → IEEE Conference on Computer Vision and P

CDnet 2014: An Expanded Change Detection Benchmark Dataset

Yi Wang, Pierre‐Marc Jodoin et al. 2014-06-01 · Read paper → BMC Psychiatry

The Beijing version of the montreal cognitive assessment as a brief screening tool for mild cognitive impairment: a community-based study

Jing Yu, Juan Li, Xin Huang 2012-09-25 · Read paper →