A Sparse Sampling-based framework for Semantic Fast-Forward of First-Person Videos

TL;DR

This paper introduces a sparse sampling framework for creating smooth, fast-forwarded first-person videos that emphasize relevant content while maintaining visual continuity, outperforming existing methods in efficiency.

Contribution

The paper proposes a novel adaptive frame selection method based on a weighted minimum reconstruction problem for semantic fast-forwarding of first-person videos.

Findings

Retains relevant information effectively

Achieves smoother transitions in fast-forward videos

Operates faster than state-of-the-art techniques

Abstract

Technological advances in sensors have paved the way for digital cameras to become increasingly ubiquitous, which, in turn, led to the popularity of the self-recording culture. As a result, the amount of visual data on the Internet is moving in the opposite direction of the available time and patience of the users. Thus, most of the uploaded videos are doomed to be forgotten and unwatched stashed away in some computer folder or website. In this paper, we address the problem of creating smooth fast-forward videos without losing the relevant content. We present a new adaptive frame selection formulated as a weighted minimum reconstruction problem. Using a smoothing frame transition and filling visual gaps between segments, our approach accelerates first-person videos emphasizing the relevant segments and avoids visual discontinuities. Experiments conducted on controlled videos and also on an unconstrained dataset of First-Person Videos (FPVs) show that, when creating fast-forward videos, our method is able to retain as much relevant information and smoothness as the state-of-the-art techniques, but in less processing time.