CrowdFix: An Eyetracking Dataset of Real Life Crowd Videos
This provides a new dataset for researchers studying visual attention in crowded scenes, but it is incremental as it focuses on a specific use case.
The authors tackled the need for diverse benchmark datasets in vision research by creating CrowdFix, an eyetracking dataset of real-life crowd videos annotated by density levels, and they evaluated state-of-the-art saliency models on it to identify improvements.
Understanding human visual attention and saliency is an integral part of vision research. In this context, there is an ever-present need for fresh and diverse benchmark datasets, particularly for insight into special use cases like crowded scenes. We contribute to this end by: (1) reviewing the dynamics behind saliency and crowds. (2) using eye tracking to create a dynamic human eye fixation dataset over a new set of crowd videos gathered from the Internet. The videos are annotated into three distinct density levels. (3) Finally, we evaluate state-of-the-art saliency models on our dataset to identify possible improvements for the design and creation of a more robust saliency model.