AI Paper Atlas

Research map / Video / Video segmentation and tracking

VideoClusterNet: Self-Supervised and Adaptive Face Clustering for Videos

Devesh Walawalkar, Pablo Garrido

ECCV 2024 · Video › Video segmentation and tracking · approach: Deepfake video detection · 3 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
add self-supervised finetuning of face ID model on the video's tracks (ablation)ArcFace-R100 + HAC · MovieFaceCluster: The Hidden Soldiercluster accuracy (%): 86.10 -> 91.52Improved
replace HAC with the proposed track clustering algorithm (cosine metric) (ablation)VideoClusterNet · MovieFaceCluster: The Hidden Soldiercluster accuracy (%): 91.52 -> 93.70Improved
use the SSL loss as similarity metric instead of cosine distance (ablation)VideoClusterNet clustering · MovieFaceCluster: The Hidden Soldiercluster accuracy (%): 93.70 -> 98.50Improved
use the SSL loss as similarity metric instead of Euclidean distance (ablation)VideoClusterNet clustering · MovieFaceCluster: The Hidden Soldierpredicted cluster ratio: 3.5 (74/21) -> 1.04 (22/21)Improved
add the finetuning method to different face ID base models (ablation)FaRL, VGGFace2, ArcFace, AdaFace · MovieFaceCluster: The Hidden Soldiercluster accuracy (%): 78.7 -> 90.2 (FaRL-P16); 86.1 -> 98.5 (ArcFace-R100)Improved
apply VideoClusterNet vs prior methods on BBT episodesBBT S01 · BBT S01 (combined)WCP (%): 94.20 -> 98.70Improved
apply VideoClusterNet vs prior methods on BVSBVS S05 · BVS S05 (combined)WCP (%): 83.62 -> 96.10Improved
apply VideoClusterNet vs VCTRSF on hardest moviesMovieFaceCluster The Fortress · MovieFaceCluster: The Fortressweighted cluster accuracy (%): 78.8 -> 89.3Improved
on BBT S1E2, VideoClusterNet vs VCTRSFBBT S01E02 · BBT S01E02WCP (%): 99.84 vs 99.67No 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