AI Paper Atlas

Research map / Video / Video segmentation and tracking

Automated Video Face Labelling for Films and TV Material

Omkar Parkhi, Esa Rahtu, Qiong Cao, Andrew Zisserman

TPAMI 2018 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use proposed bag formation around subtitle tracks instead of prior bag strategiesMIL face labelling (CNN) · Buffyaverage precision: 0.93 -> 0.96Improved
add speaker detection to bag formation (ablation)Ours (CNN) · Buffyaverage precision: 0.94 -> 0.96Improved
add speaker detection to bag formation (ablation)Ours (FV) · Buffyaverage precision: 0.88 -> 0.91Improved
add speaker detection (bag size shrinks) (ablation)Our bags · Buffy episode 1average positive bag size: 2.1 -> 1.4 average bag sizeImproved
change initialisation of learning algorithm (random vs other methods) (ablation)Ours · Buffy episodes 1-5average precision: 0.9 vs 0.89No clear effect
add our learning algorithm and bag formation (with negative bags) to baseline (ablation)Baseline [2] components · Casablancaaverage precision: 0.75 -> 0.85Improved
add background character classifier to [2] components (ablation)Baseline [2] components · Casablancaaverage precision: 0.75 -> 0.80Improved
add background character classifier to our learning and bags (ablation)Ours · Casablancaaverage precision: 0.85 -> 0.88Improved
replace [2] track features with our CNN track features (ablation)Ours · Casablancaaverage precision: 0.88 -> 0.93Improved
add linear programming track labelling constraint (ablation)Ours · Casablancaaverage precision: 0.93 -> 0.93No clear effect
add linear programming track labelling constraint (ablation)Ours · Buffyaverage precision: 0.96 -> 0.96No clear effect
add linear programming track labelling constraint (ablation)Ours · Big Bang Theoryaverage precision: 0.95 -> 0.96Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy