In the Eye of the Beholder: Gaze and Actions in First Person Video
Citations Over TimeTop 10% of 2021 papers
Abstract
We address the task of jointly determining what a person is doing and where they are looking based on the analysis of video captured by a headworn camera. To facilitate our research, we first introduce the EGTEA Gaze+ dataset. Our dataset comes with videos, gaze tracking data, hand masks and action annotations, thereby providing the most comprehensive benchmark for First Person Vision (FPV). Moving beyond the dataset, we propose a novel deep model for joint gaze estimation and action recognition in FPV. Our method describes the participant's gaze as a probabilistic variable and models its distribution using stochastic units in a deep network. We further sample from these stochastic units, generating an attention map to guide the aggregation of visual features for action recognition. Our method is evaluated on our EGTEA Gaze+ dataset and achieves a performance level that exceeds the state-of-the-art by a significant margin. More importantly, we demonstrate that our model can be applied to larger scale FPV dataset-EPIC-Kitchens even without using gaze, offering new state-of-the-art results on FPV action recognition.
Related Papers
- → An Object Detection and Pose Estimation Approach for Position Based Visual Servoing(2017)5 cited
- → Self-monitoring to improve robustness of 3D object tracking for robotics(2011)4 cited
- → Foreground object segmentation from binocular stereo video(2005)2 cited
- → 6-DOF object localization by combining monocular vision and robot arm kinematics(2017)1 cited
- Eye Tracking Gaze Estimation Based on Marker Detection(2011)