AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Group Activity Prediction with Sequential Relational Anticipation Model

Junwen Chen, Wentao Bao, Yu Kong

ECCV 2020 · Graph learning › Knowledge and temporal graphs · approach: Continuous-time dynamic graph learning · 19 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 position regression loss and position prediction (ablation)SRAM · Volleyball (avg 10/40/70% observed)accuracy (%): 84.85 -> 86.85Improved
add adversarial loss (ablation)SRAM · Volleyball (avg 10/40/70% observed)accuracy (%): 86.30 -> 86.85Improved
add sequential reconstruction loss (ablation)SRAM · Volleyball (avg 10/40/70% observed)accuracy (%): 86.22 -> 86.85Improved
use 5 unrolling stages instead of 1 (ablation)SRAM · Volleyball (avg 10/40/70% observed)accuracy (%): 81.47 -> 86.85Improved
use 5 unrolling stages instead of 2 (ablation)SRAM · Volleyball (avg 10/40/70% observed)accuracy (%): 85.22 -> 86.85Improved
use 10 unrolling stages instead of 5 (ablation)SRAM · Volleyball (avg 10/40/70% observed)accuracy (%): 86.85 -> 86.79No clear effect
use 5 stages instead of 1 at low observation ratio (ablation)SRAM · Volleyball (10% observed)accuracy (%): 70.38 -> 77.86Improved
use SRAM instead of e-AAPNet with trackletsSRAM · Collective Activity (50% observed)accuracy (%): 86.01 -> 92.55Improved
use SRAM instead of ARG at low observationSRAM · Volleyball (10% observed)accuracy (%): 64.82 -> 77.86Improved
predict positions with SRAM instead of SocialGANSRAM · Volleyball position predictionFDE: 5.32 -> 3.62Improved
add tracklet information to AAPNet (e-AAPNet)SRAM · Volleyball (100% observed)accuracy (%): 80.78 -> 89.01Improved

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