High-Level Features for Movie Style Understanding - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

High-Level Features for Movie Style Understanding

Abstract

Automatically analysing stylistic features in movies is a challenging task, as it requires an in-depth knowledge of cinematography. In the literature, only a handful of methods explore stylistic feature extraction, and they typically focus on limited low-level image and shot features (colour histograms, average shot lengths or shot types, amount of camera motion). These, however, only capture a subset of the stylistic features which help to characterise a movie (e.g. black and white vs. coloured, or film editing). To this end, in this work, we systematically explore seven high-level features for movie style analysis: character segmentation, pose estimation, depth maps, focus maps, frame layering, camera motion type and camera pose. Our findings show that low-level features remain insufficient for movie style analysis, while high-level features seem promising.
Fichier principal
Vignette du fichier
movie_style.pdf (8.67 Mo) Télécharger le fichier
movie_style_supp.pdf (917.55 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03381587 , version 1 (17-10-2021)

Identifiers

  • HAL Id : hal-03381587 , version 1

Cite

Robin Courant, Christophe Lino, Marc Christie, Vicky Kalogeiton. High-Level Features for Movie Style Understanding. ICCV 2021 - Workshop on AI for Creative Video Editing and Understanding, Oct 2021, online, France. pp.1-5. ⟨hal-03381587⟩
393 View
142 Download

Share

Gmail Mastodon Facebook X LinkedIn More