AI Paper Atlas

Research map / Video / Action recognition

Social Adaptive Module for Weakly-supervised Group Activity Recognition

Rui Yan, Lingxi Xie, Jinhui Tang, Xiangbo Shu, Qi Tian

ECCV 2020 · Video › Action recognition · approach: Temporal action segmentation · 119 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 Spatial-SAM selecting 8 of 14 proposals (pruning) (ablation)Ours baseline · NBAaccuracy (%): 44.6 -> 50.3Improved
add Spatial-SAM relational embedding without pruning (14 proposals) (ablation)Ours baseline · NBAaccuracy (%): 44.6 -> 46.8Improved
add pruning of proposals (Kp=8 from Np=14) on top of unpruned SAM (ablation)Spatial-SAM · NBAaccuracy (%): 46.8 -> 50.3Improved
add Temporal-SAM to Spatial-SAM (ablation)Spatial-SAM (B3) · NBAmean accuracy (%): 43.6 -> 47.5Improved
add Temporal-SAM to Spatial-SAM (ablation)Spatial-SAM (B3) · NBAaccuracy (%): 50.3 -> 49.1Hurt
use probability-aware instead of quantity-aware proposal count (ablation)Spatial-SAM (Kp=8) · NBAmean accuracy (%): 43.6 -> 42.6Hurt
add Spatial-SAM with pruning to the base model (ablation)Ours w/o SAM · NBAmean accuracy (%): 39.5 -> 43.6Improved
add Spatial-SAM with pruning (Np=16, Kp=12) (ablation)Ours baseline · Volleyball Dataset (weak supervision)accuracy (%): 91.5 -> 93.1Improved
add SAM relational embedding without pruning (Np=16, Kp=16) (ablation)Ours baseline · Volleyball Dataset (weak supervision)accuracy (%): 91.5 -> 92.4Improved
use fewer input proposals without pruning (Np=12, Kp=12) (ablation)Spatial-SAM · Volleyball Dataset (weak supervision)accuracy (%): 91.5 -> 91.9No clear effect
train ARG with only video-level labels instead of full supervisionARG · Volleyball Datasetaccuracy (%): 94.0 -> 90.7Hurt
switch SAM backbone from ResNet-18 to Inception-v3Ours (weakly supervised) · Volleyball Datasetaccuracy (%): 93.1 -> 94.0Improved

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