AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Situation Recognition With Graph Neural Networks

Ruiyu Li, Makarand Tapaswi, Renjie Liao, Jiaya Jia, Raquel Urtasun, Sanja Fidler

ICCV 2017 · Graph learning › Knowledge and temporal graphs · approach: Graph-based dialog systems · 143 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 graph propagation (T=1) over role nodes versus unaries only (ablation)FC Graph GGNN · imSitu devmean over all metrics: 35.08 -> 38.83Improved
increase propagation steps from T=1 to T=4 (ablation)FC Graph GGNN · imSitu devmean over all metrics: 38.83 -> 39.19Improved
add beam search with width 10 (ablation)FC Graph GGNN T=4 · imSitu devmean over all metrics: 39.19 -> 39.39Improved
add beam search with width 10 to unaries (ablation)Unaries · imSitu devmean over all metrics: 35.08 -> 35.16Improved
initialize role nodes with predicted verb embedding (vOH) (ablation)FC Graph GGNN T=4, BS=10 · imSitu dev (top-1 predicted verb)value-all: 17.70 -> 19.15Improved
use ReLU instead of tanh for initialization nonlinearity (ablation)FC Graph GGNN with vOH · imSitu devmean over all metrics: 41.32 -> 41.46No clear effect
use Soft-OR loss instead of loss predicting all annotations (ablation)FC Graph GGNN with vOH · imSitu devmean over all metrics: 41.32 -> 40.95Hurt
order roles verb, agent, place rather than verb, place, agent in chain RNN (ablation)Chain RNN · imSituperformance: 1.9% dropHurt
add chain RNN over roles versus unaries (ablation)Unaries · imSitu dev (top-1 predicted verb)value-all: 14.01 -> 17.94Improved
add tree-structured RNN over roles versus unaries (ablation)Unaries · imSitu dev (top-1 predicted verb)value-all: 14.01 -> 16.04Improved
use GGNN instead of RNN on a chain of rolesChain structure · imSitu devmean over all metrics: 38.36 -> 40.95Improved
connect roles in a fully connected graph instead of tree structure (ablation)GGNN · imSitu devmean over all metrics: 41.29 -> 41.32Improved

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