AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Towards More Practical Group Activity Detection: A New Benchmark and Model

Dongkeun Kim, Youngkil Song, Minsu Cho, Suha Kwak

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 11 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 group consistency loss (InfoNCE variant on actor embeddings) (ablation)Grouping Transformer GAD model · Cafe split by viewGroup mAPImproved
keep grouping-attention layer in Grouping Transformer (ablation)Grouping Transformer · Cafe split by viewGroup mAPImproved
keep self-attention and cross-attention layers (ablation)Grouping Transformer · Cafe split by viewGroup mAPImproved
apply distance mask with threshold 0.2 on actor self-attention (ablation)Grouping Transformer · Cafe split by viewGroup mAPImproved
use too small distance mask threshold 0.1 (ablation)Grouping Transformer · Cafe split by viewGroup mAPHurt
increase number of group tokens from 12 to 16 (ablation)Grouping Transformer · Cafe split by viewGroup mAP@1.0: 18.84 -> 15.03Hurt
match actors to groups in embedding space instead of 2D point matching (HGC)Transformer GAD · Cafe split by viewGroup mAP@1.0: 6.55 -> 18.84Improved
replace off-the-shelf clustering with learnable group tokensGAD pipeline · Cafe inference timeinference time (s): 0.32 -> 0.10Improved
vary number of clusters for clustering-based methods (ablation)ARG baseline · Cafe split by viewGroup mAP@1.0: 11.03 (4) -> 1.27 (6)Mixed
use detection-based tracklets instead of ground-truth trackletsGrouping Transformer · Cafe split by viewGroup mAP@1.0: 18.84 -> 14.36Hurt

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