Videogenic: Identifying Highlight Moments in Videos with Professional Photographs as a Prior

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lin, David Chuan-En, Heilbron, Fabian Caba, Lee, Joon-Young, Wang, Oliver, Martelaro, Nikolas
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914848324976640
author Lin, David Chuan-En
Heilbron, Fabian Caba
Lee, Joon-Young
Wang, Oliver
Martelaro, Nikolas
author_facet Lin, David Chuan-En
Heilbron, Fabian Caba
Lee, Joon-Young
Wang, Oliver
Martelaro, Nikolas
contents This paper investigates the challenge of extracting highlight moments from videos. To perform this task, we need to understand what constitutes a highlight for arbitrary video domains while at the same time being able to scale across different domains. Our key insight is that photographs taken by photographers tend to capture the most remarkable or photogenic moments of an activity. Drawing on this insight, we present Videogenic, a technique capable of creating domain-specific highlight videos for a diverse range of domains. In a human evaluation study (N=50), we show that a high-quality photograph collection combined with CLIP-based retrieval (which uses a neural network with semantic knowledge of images) can serve as an excellent prior for finding video highlights. In a within-subjects expert study (N=12), we demonstrate the usefulness of Videogenic in helping video editors create highlight videos with lighter workload, shorter task completion time, and better usability.
format Preprint
id arxiv_https___arxiv_org_abs_2211_12493
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Videogenic: Identifying Highlight Moments in Videos with Professional Photographs as a Prior
Lin, David Chuan-En
Heilbron, Fabian Caba
Lee, Joon-Young
Wang, Oliver
Martelaro, Nikolas
Computer Vision and Pattern Recognition
Human-Computer Interaction
Multimedia
This paper investigates the challenge of extracting highlight moments from videos. To perform this task, we need to understand what constitutes a highlight for arbitrary video domains while at the same time being able to scale across different domains. Our key insight is that photographs taken by photographers tend to capture the most remarkable or photogenic moments of an activity. Drawing on this insight, we present Videogenic, a technique capable of creating domain-specific highlight videos for a diverse range of domains. In a human evaluation study (N=50), we show that a high-quality photograph collection combined with CLIP-based retrieval (which uses a neural network with semantic knowledge of images) can serve as an excellent prior for finding video highlights. In a within-subjects expert study (N=12), we demonstrate the usefulness of Videogenic in helping video editors create highlight videos with lighter workload, shorter task completion time, and better usability.
title Videogenic: Identifying Highlight Moments in Videos with Professional Photographs as a Prior
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
Multimedia
url https://arxiv.org/abs/2211.12493