AI Paper Atlas

Research map / Video / Video segmentation and tracking

Self-supervised Video-centralised Transformer for Video Face Clustering

Yujiang Wang, Mingzhi Dong, Jie Shen, Yiming Luo, Yiming Lin, Pingchuan Ma, Stavros Petridis, Maja Pantić

TPAMI 2023 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning

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
introduce video centres with naive options (uniform sampler, last-forward centres, incremental lr) (ablation)CT TRSF. · EasyCom-Clustering V04 (known clusters)NMI (%): 85.20 -> 83.54Hurt
use consecutive temporal sampler instead of uniform sampler (ablation)VC TRSF. · EasyCom-Clustering V04 (known clusters)NMI (%): 83.54 -> 83.97Improved
represent centres with incomplete centre algorithm instead of last-forward value (ablation)VC TRSF. · EasyCom-Clustering V04 (known clusters)NMI (%): 83.97 -> 86.20Improved
add periodic re-computation of video centres (complete algorithm) (ablation)VC TRSF. · EasyCom-Clustering V04 (known clusters)NMI (%): 86.20 -> 87.19Improved
make centre learning rate proportional to network learning rate (ablation)VC TRSF. · EasyCom-Clustering V04 (known clusters)NMI (%): 87.19 -> 90.69Improved
add scaled positional embedding (ablation)VC TRSF. · EasyCom-Clustering V08 (known clusters)NMI (%): 86.70 -> 84.53Hurt
add interpolated positional embedding (ablation)VC TRSF. · EasyCom-Clustering V08 (known clusters)NMI (%): 86.70 -> 85.89No clear effect
train transformer with video centres instead of pairwise contrastCT TRSF. · BBT (known clusters)NMI (%): 91.86 -> 94.20Improved
train transformer with video centres instead of pairwise contrastCT TRSF. · BBT (unknown clusters)cluster number difference: 76 -> 56Improved
replace TSiam with video-centralised transformerTSiam · BBT (known clusters)NMI (%): 94.11 -> 94.20No clear effect
learn a Siamese MLP (SSiam) instead of temporal averagingTemp. AVG · EasyCom-Clustering (known clusters)WCP (%): 78.44 -> 93.07Improved

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