High-Level Features for Movie Style Understanding

Robin Courant (1, 2, 3, 4) , Christophe Lino (1, 2, 3, 4) , Marc Christie (5) , Vicky Kalogeiton (1, 2, 3, 4)

1 LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
2 X-DEP-INFO - Département d'informatique de l'École polytechnique
3 CNRS - Centre National de la Recherche Scientifique
4 IP Paris - Institut Polytechnique de Paris
5 MIMETIC - Analysis-Synthesis Approach for Virtual Human Simulation

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.

Mots clés: film analysis; deep learning; movie style understanding

Domaines: Synthèse d'image et réalité virtuelle [cs.GR]; Interface homme-machine [cs.HC]; Intelligence artificielle [cs.AI]; Multimédia [cs.MM]

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⟩