AI Paper Atlas

Research map / Detection and segmentation / CNN features

End-To-End Face Detection and Cast Grouping in Movies Using Erdos-Renyi Clustering

SouYoung Jin, Hang Su, Chris Stauffer, Erik Learned-Miller

ICCV 2017 · Detection and segmentation › CNN features · approach: Pedestrian and crowd detection

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 rank-1 counts instead of L2 distance for link-based clusteringlink-based clustering · HannahF0.5: .2581 -> .6813Improved
use rank-1 counts instead of L2 distance for link-based clusteringlink-based clustering · Buffy s05 (avg of 6 episodes)F0.5: .3931 -> .6299Improved
use rank-1 counts instead of L2 distance for link-based clusteringlink-based clustering · BBT s01 (avg of 6 episodes)F0.5: .7365 -> .7828Improved
use rank-1 counts instead of L2 distance for link-based clusteringlink-based clustering · LFWpairwise F0.5: .8498 -> .8943Improved
use rank-1 counts instead of L2 in verification at FPR 1E-9verification · LFW all-pairs verificationrecall: 0.0068 -> 0.0252Improved
use rank-1 counts instead of L2 in verification at FPR 1E-6verification · LFW all-pairs verificationrecall: 0.1279 -> 0.1872Improved
use rank-1 counts instead of rank-order distance at FPR 1E-3verification · LFW all-pairs verificationrecall: 0.8719 -> 0.8222Hurt
use rank-1 counts instead of template adaptationlink-based clustering · LFWpairwise F0.5: .3735 -> .8943Improved
use automatically estimated threshold instead of oracle threshold for rank-1 countsRank-1 Count · HannahF0.5: .6813 -> .6436Hurt
use automatically estimated threshold instead of oracle threshold for rank-1 countsRank-1 Count · Buffy s05 (avg of 6 episodes)F0.5: .6299 -> .5661Hurt
use automatically estimated threshold instead of oracle threshold for rank-1 countsRank-1 Count · LFWpairwise F0.5: .8943 -> .8532Hurt
use automatically estimated threshold instead of oracle threshold for rank-1 countsRank-1 Count · BBT s01 (avg of 6 episodes)F0.5: .7828 -> .7728No clear effect

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