Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition

Abstract

We present a new computational model for gaze prediction in egocentric videos by exploring patterns in temporal shift of gaze fixations (attention transition) that are dependent on egocentric manipulation tasks. Our assumption is that the high-level context of how a task is completed in a certain way has a strong influence on attention transition and should be modeled for gaze prediction in natural dynamic scenes. Specifically, we propose a hybrid model based on deep neural networks which integrates task-dependent attention transition with bottom-up saliency prediction. In particular, the task-dependent attention transition is learned with a recurrent neural network to exploit the temporal context of gaze fixations, e.g. looking at a cup after moving gaze away from a grasped bottle. Experiments on public egocentric activity datasets show that our model significantly outperforms state-of-the-art gaze prediction methods and is able to learn meaningful transition of human attention.

arXiv commentAccepted as oral presentation in ECCV 2018

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Two-Stream Convolutional Networks for Action Recognition in Videos
• Convolutional Two-Stream Network Fusion for Video Action Recognition
• Shallow and Deep Convolutional Networks for Saliency Prediction
• Recurrent Attentional Networks for Saliency Detection

Cited by in corpus (4)

• EyeNet: A Multi-Task Network for Off-Axis Eye Gaze Estimation and User Understanding
• ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery
• MagicEyes: A Large Scale Eye Gaze Estimation Dataset for Mixed Reality
• Temporal Saliency Adaptation in Egocentric Videos