AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Hunting Group Clues with Transformers for Social Group Activity Recognition

Masato Tamura, Rahul Vishwakarma, Ravigopal Vennelakanti

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 46 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
sort group member points by X coordinate rather than Y (ablation)Ours · Volleyball social group activityaccuracy: 55.5 -> 60.6Improved
add group annotations to training (ablation)Ours · Volleyball group activityaccuracy: 95.0 -> 96.0Improved
add group annotations to training (ablation)GroupFormer · Volleyball group activity (detection-based)accuracy: 95.0 -> 93.2Hurt
add group annotations to training (ablation)GroupFormer · Volleyball group activity (ground-truth boxes)accuracy: 95.7 -> 96.1Improved
replace region features with transformer-generated group features (ours vs GroupFormer) (ablation)Ours · Volleyball social group activityaccuracy: 48.8 -> 60.6Improved
replace region features with transformer-generated group features (ours vs Ehsanpour et al.) (ablation)Ours · Volleyball social group activityaccuracy: 44.5 -> 60.6Improved
use our method instead of Ehsanpour et al. for Collective Activity social groups (ablation)Ours · Collective Activity social group activitymAP: 51.3 -> 46.0Hurt
use predicted rather than ground-truth boxes (ablation)GroupFormer · Volleyball group activityaccuracy: 95.7 -> 95.0Hurt
use predicted rather than ground-truth boxes (ablation)GroupFormer · Collective Activity group activityaccuracy: 96.3 -> 85.2Hurt
rely on learned group size with few training samples (size 4 on Collective Activity) (ablation)Ours · Collective Activity TalkingmAP: 6.56Hurt
larger training data ratio for group size (ablation)Ours · Volleyball group size analysisaccuracy: 83.6 at 36% vs 26.1 at 6%Improved
our method vs Ehsanpour et al. on group size 3Ours · Volleyball group size 3accuracy: 61.2 -> 52.4Hurt

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