AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Mixture-Kernel Graph Attention Network for Situation Recognition

Mohammed Suhail, Leonid Sigal

ICCV 2019 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 35 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 attention to GGNN (ablation)GGNN · imSitu testmean score: 38.19 -> 39.89Improved
add hard-assigned multi-kernel to GGNN (ablation)GGNN · imSitu testmean score: 38.19 -> 39.27Improved
add attention to multi-kernel GGNN (ablation)GGNN + multi-kernel · imSitu testmean score: 39.27 -> 40.99Improved
replace hard multi-kernel with mixture-kernel (convex combination of shared basis) with attention (ablation)GGNN + attn · imSitu testmean score: 40.99 -> 42.66Improved
full model (mixture-kernel + attention) vs naive GGNN, ground truth verb (ablation)GGNN · imSitu testvalue (ground truth verb): 67.32 -> 72.92Improved
increase propagation steps from T=0 to T=4 (ablation)Ours · imSituvalue: 58.13 -> 72.93Improved
increase propagation steps from T=3 to T=4 (ablation)Ours · imSituvalue: 72.18 -> 72.93Improved
use predicted basis weights instead of random permuted weights (value) (ablation)Ours · imSitu (GT verb)value: 64.26 -> 72.96Improved
use predicted basis weights instead of random permuted weights (value-all) (ablation)Ours · imSitu (GT verb)value-all: 26.85 -> 42.35Improved
keep all edges rather than removing 75% at random (ablation)Ours · imSitu (GT verb)value: 61.18 -> 72.93Improved
Ours vs Fully-connected Graph with top-1 predicted verbOurs · imSitu testvalue: 27.52 -> 35.41Improved
Ours vs Fully-connected Graph with top-5 predicted verbOurs · imSitu testvalue: 45.39 -> 55.62Improved

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