Gaze Pattern Recognition in Dyadic Communication
Open Access
- 30 May 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Abstract
Analyzing gaze behaviors is crucial to interpret the nature of communication. Current studies on gaze have focused primarily on the detection of a single pattern, such as the Looking-At-Each-Other pattern or the shared attention pattern. In this work, we re-define five static gaze patterns that cover all the status during a dyadic communication and propose a network to recognize these mutual exclusive gaze patterns given an image. We annotate a benchmark, called GP-Static, for the gaze pattern recognition task, on which our method experimentally outperforms other alternate solutions. Our method also achieves the state-of-art performance on other two single gaze pattern recognition tasks. The analysis of gaze patterns on preschool children demonstrates that the statistic of the proposed static gaze patterns conforms with the findings in psychology.Keywords
Funding Information
- National Key R&D Program of China (2018AAA0102405)
- National Natural Science Foundation of China (62176248)
- Project of Shanghai Education Commission (2023SKZD07)
This publication has 7 references indexed in Scilit:
- Dual Attention Guided Gaze Target Detection in the Wild2021
- Vision-Based Gaze Estimation: A ReviewIEEE Transactions on Cognitive and Developmental Systems, 2021
- LAEO-Net++: Revisiting People Looking at Each Other in VideosIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset TransferIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Detecting Attended Visual Targets in Video2020
- Automatic editing of footage from multiple social camerasACM Transactions on Graphics, 2014
- Detecting People Looking at Each Other in VideosInternational Journal of Computer Vision, 2013