Face, Body, Voice: Video Person-Clustering with Multiple Modalities - École polytechnique Access content directly
Conference Papers Year : 2021

Face, Body, Voice: Video Person-Clustering with Multiple Modalities

Andrew Brown
  • Function : Author
  • PersonId : 1111161
Andrew Zisserman
  • Function : Author
  • PersonId : 878447

Abstract

The objective of this work is person-clustering in videos-grouping characters according to their identity. Previous methods focus on the narrower task of face-clustering, and for the most part ignore other cues such as the person's voice, their overall appearance (hair, clothes, posture), and the editing structure of the videos. Similarly, most current datasets evaluate only the task of face-clustering, rather than person-clustering. This limits their applicability to downstream applications such as story understanding which require person-level, rather than only face-level, reasoning. In this paper we make contributions to address both these deficiencies: first, we introduce a Multi-Modal High-Precision Clustering algorithm for person-clustering in videos using cues from several modalities (face, body, and voice). Second, we introduce a Video Person-Clustering dataset, for evaluating multi-modal person-clustering. It contains body-tracks for each annotated character, facetracks when visible, and voice-tracks when speaking, with their associated features. The dataset is by far the largest of its kind, and covers films and TV-shows representing a wide range of demographics. Finally, we show the e ectiveness of using multiple modalities for person-clustering, explore the use of this new broad task for story understanding through character co-occurrences, and achieve a new state of the art on all available datasets for face and person-clustering.
Fichier principal
Vignette du fichier
ICCV-W-2021-FaceBodyVoice.pdf (4.72 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03353619 , version 1 (24-09-2021)

Identifiers

  • HAL Id : hal-03353619 , version 1

Cite

Andrew Brown, Vicky Kalogeiton, Andrew Zisserman. Face, Body, Voice: Video Person-Clustering with Multiple Modalities. International Conference on Computer Vision (ICCV) 2021 Workshop on AI for Creative Video Editing and Understanding, Oct 2021, Montreal (virtual), Canada. ⟨hal-03353619⟩
73 View
214 Download

Share

Gmail Facebook X LinkedIn More