# Are all the frames equally important?

## TL;DR

This paper introduces a new interactive cursor-based method for measuring and predicting the importance of entire video frames for human attention, enabling scalable data collection for temporal saliency analysis.

## Contribution

It presents the first human response dataset for temporal video saliency using an accessible, cursor-based interface that correlates well with eye-tracking data.

## Key findings

- Scores reflect semantic changes in frames
- High correlation among observers' responses
- Tool can replace eye-tracking for data collection

## Abstract

In this work, we address the problem of measuring and predicting temporal video saliency - a metric which defines the importance of a video frame for human attention. Unlike the conventional spatial saliency which defines the location of the salient regions within a frame (as it is done for still images), temporal saliency considers importance of a frame as a whole and may not exist apart from context. The proposed interface is an interactive cursor-based algorithm for collecting experimental data about temporal saliency. We collect the first human responses and perform their analysis. As a result, we show that qualitatively, the produced scores have very explicit meaning of the semantic changes in a frame, while quantitatively being highly correlated between all the observers. Apart from that, we show that the proposed tool can simultaneously collect fixations similar to the ones produced by eye-tracker in a more affordable way. Further, this approach may be used for creation of first temporal saliency datasets which will allow training computational predictive algorithms. The proposed interface does not rely on any special equipment, which allows to run it remotely and cover a wide audience.