· 2015
Appearance-based gaze estimation in the wild
- 736citations
- 2015year
Short summary
A new dataset (MPIIGaze) of 213,659 images collected during natural laptop use, and a multimodal CNN method, significantly outperform state-of-the-art for appearance-based gaze estimation in uncontrolled environments.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduced MPIIGaze, a dataset of 213,659 images from 15 participants during natural laptop use.
- MPIIGaze exhibits greater variability in appearance and illumination than existing datasets.
- A multimodal CNN method was developed for in-the-wild gaze estimation.
- The proposed method significantly outperforms state-of-the-art in cross-dataset evaluations.
AI-generated from the title and abstract; the full text is not read.
Abstract
Appearance-based gaze estimation is believed to work well in real-world settings, but existing datasets have been collected under controlled laboratory conditions and methods have been not evaluated across multiple datasets. In this work we study appearance-based gaze estimation in the wild. We present the MPIIGaze dataset that contains 213,659 images we collected from 15 participants during natural everyday laptop use over more than three months. Our dataset is significantly more variable than existing ones with respect to appearance and illumination. We also present a method for in-the-wild appearance-based gaze estimation using multimodal convolutional neural networks that significantly outperforms state-of-the art methods in the most challenging cross-dataset evaluation. We present an extensive evaluation of several state-of-the-art image-based gaze estimation algorithms on three current datasets, including our own. This evaluation provides clear insights and allows us to identify key research challenges of gaze estimation in the wild.
The authors' abstract, as published at the source., 2015 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Human-Computer Interaction
Human-Computer InteractionComputer Science