AI Paper Atlas

Research map / Video / Video segmentation and tracking

Towards Scene Graph Anticipation

Rohith Peddi, Saksham Singh, Saurabh ., Parag Singla, Vibhav Gogate

ECCV 2024 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 10 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 temporal encoder and dual decoding of observed and anticipated relationships (baseline+ to baseline++) (ablation)STTran / DSGDetr anticipation baselines · Action Genome AGS, 30% observed, With ConstraintR@10: 12.5 -> 18.5 (STTran), 12.8 -> 19.5 (DSGDetr)Improved
replace anticipatory transformer with NeuralODE latent dynamics (SceneSayerODE)anticipation baselines · Action Genome AGS, 30% observed, With ConstraintR@10: 19.5 -> 23.1Improved
use NeuralSDE instead of NeuralODE for latent dynamics (ablation)SceneSayer · Action Genome AGS, 30% observed, With ConstraintR@10: 23.1 -> 25.0Improved
use SceneSayerSDE on No Constraint R@50SceneSayer · Action Genome AGS, 30% observed, No ConstraintR@50: 48.9 -> 47.4Hurt
use SceneSayerSDE instead of best baselinescene graph anticipation · Action Genome AGSR@10: up to ~70% betterImproved
use SceneSayerSDE instead of best baselinescene graph anticipation · Action Genome PGAGSR@10: up to ~30% improvementImproved
use SceneSayerSDE instead of best baselinescene graph anticipation · Action Genome GAGSR@10: approximately 26% improvementImproved
use SceneSayer ODE/SDE for mean recallscene graph anticipation · Action Genome AGS, 30% observed, With ConstraintmR@10: 5.9 -> 11.4Improved
freeze pre-trained ORPU and SCPU and train only LDPU instead of end-to-end training (ablation)SceneSayer · Action GenomeRecall (qualitative)Hurt
remove objects violating continuity from the test set (ablation)all methods · Action Genome GAGS, 30% observed, No ConstraintR@10: 46.9 -> 70.9 (SceneSayerSDE)Improved
provide more scene information (AGS to PGAGS to GAGS) (ablation)SceneSayerSDE · Action Genome, 30% observed, With ConstraintR@10: 25.0 -> 28.8 -> 39.7Improved

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