# Subjective Annotations for Vision-Based Attention Level Estimation

## TL;DR

This paper introduces a new subjective annotation framework for attention levels, annotates over 100,000 images, and proposes a geometric feature-based deep learning method achieving 80% accuracy in vision-based attention estimation.

## Contribution

It presents a novel subjective annotation approach and a geometric feature-based deep learning method for attention level estimation from RGB and depth images.

## Key findings

- Achieved 80.02% accuracy in attention level estimation.
- Annotated over 100,000 images with subjective attention levels.
- Provided publicly available dataset and framework.

## Abstract

Attention level estimation systems have a high potential in many use cases, such as human-robot interaction, driver modeling and smart home systems, since being able to measure a person's attention level opens the possibility to natural interaction between humans and computers. The topic of estimating a human's visual focus of attention has been actively addressed recently in the field of HCI. However, most of these previous works do not consider attention as a subjective, cognitive attentive state. New research within the field also faces the problem of the lack of annotated datasets regarding attention level in a certain context. The novelty of our work is two-fold: First, we introduce a new annotation framework that tackles the subjective nature of attention level and use it to annotate more than 100,000 images with three attention levels and second, we introduce a novel method to estimate attention levels, relying purely on extracted geometric features from RGB and depth images, and evaluate it with a deep learning fusion framework. The system achieves an overall accuracy of 80.02%. Our framework and attention level annotations are made publicly available.