AI Paper Atlas

Research map / Video / Action recognition

GroupFormer: Group Activity Recognition With Clustered Spatial-Temporal Transformer

Shuaicheng Li, Qianggang Cao, Lingbo Liu, Kunlin Yang, Shinan Liu, Jun Hou, Shuai Yi

ICCV 2021 · Video › Action recognition · approach: Disentangled action recognition · 169 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 the full CSTT (cross-decoder spatial-temporal transformer) instead of an FC layer (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 91.0 -> 94.1Improved
add cross individual decoders to parallel encoders (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 92.2 -> 94.1Improved
model spatial and temporal context in parallel rather than spatial only (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 91.8 -> 92.2Improved
stack spatial and temporal encoders versus parallel summation (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 92.2 -> 92.6Improved
add clustered attention (4 clusters) to the spatial-temporal transformer (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 93.4 -> 94.1Improved
increase clusters from 4 to 6 (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 94.1 -> 93.4Hurt
add intra-group attention only (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 93.4 -> 93.8Improved
add inter-group attention only (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 93.4 -> 93.6Improved
combine intra- and inter-group attention (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 93.4 -> 94.1Improved
use one CSTT block instead of FC layer (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 91.0 -> 93.6Improved
stack 3 CSTT blocks instead of 1 (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 93.6 -> 94.1Improved
stack 4 CSTT blocks instead of 3 (ablation)GroupFormer · Volleyball val (Inception-v3)group activity accuracy: 94.1 -> 93.9Hurt

Later papers that compared with this method

1 later accepted paper reports GroupFormer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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