A gaze driven fast-forward method for first-person videos

TL;DR

This paper introduces a gaze-driven fast-forward technique for first-person videos that emphasizes important moments based on visual attention, enabling efficient review of lengthy recordings by highlighting significant interactions.

Contribution

It presents a novel attention model utilizing gaze and scene analysis to selectively accelerate first-person videos, focusing on meaningful interactions and reducing monotonous segments.

Findings

Effectively emphasizes important moments in first-person videos.

Reduces viewing time by skipping monotonous segments.

Validated on publicly available datasets with positive results.

Abstract

The growing data sharing and life-logging cultures are driving an unprecedented increase in the amount of unedited First-Person Videos. In this paper, we address the problem of accessing relevant information in First-Person Videos by creating an accelerated version of the input video and emphasizing the important moments to the recorder. Our method is based on an attention model driven by gaze and visual scene analysis that provides a semantic score of each frame of the input video. We performed several experimental evaluations on publicly available First-Person Videos datasets. The results show that our methodology can fast-forward videos emphasizing moments when the recorder visually interact with scene components while not including monotonous clips.