Computational Methods for Measurement of Visual Attention from Videos towards Large-Scale Behavioral Analysis
Author(s)
Chong, Eun Ji
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Visual attention is one of the most important aspects of human social behavior, visual navigation, and interaction with the world, revealing information about their social, cognitive, and affective states. Although monitor-based and wearable eye trackers are widely available, they are not sufficient to support the large-scale collection of naturalistic gaze data in face-to-face social interactions or during interactions with 3D environments. Wearable eye trackers are burdensome to participants and bring issues of calibration, compliance, cost, and battery life. The ability to automatically measure attention from ordinary videos would deliver scalable, dense, and objective measurements to use in practice.
This thesis investigates several computational methods to measure visual attention from videos using computer vision and its use for quantifying visual social cues such as eye contact and joint attention. Specifically, three methods are investigated. First, I present methods for detection of looks to camera in first-person view and its use for eye contact detection. Experimental results show that the presented method can achieve the first human expert-level detection of eye contact. Second, I develop a method for tracking heads in a 3d space for measuring attentional shifts. Lastly, I propose spatiotemporal deep neural networks for detecting time-varying attention targets in video and present its application for the detection of shared attention and joint attention. The method achieves state-of-the-art results on different benchmark datasets on attention measurement as well as the first empirical result on clinically-relevant gaze shift classification.
Presented approaches have the benefit of linking gaze estimation to the broader tasks of action recognition and dynamic visual scene understanding, and bears potential as a useful tool for understanding attention in various contexts such as human social interactions, skill assessments, and human-robot interactions.
Sponsor
Date
2020-02-18
Extent
Resource Type
Text
Resource Subtype
Dissertation