AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Attention-Based Context Aware Reasoning for Situation Recognition

Thilini Cooray, Ngai-Man Cheung, Wei Lu

CVPR 2020 · Vision-language and multimodal › Visual question answering · approach: Visual reasoning diagnostics · 28 citations (OpenAlex)

Check 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 attention-weighted context from neighboring roles to each role query (CAQ) (ablation)TDA frame recognition · imSitu developmentvalue accuracy: 72.96 -> 73.62Improved
Add attention-weighted context from neighboring roles to each role query (CAQ) (ablation)TDA frame recognition · imSitu developmentvalue-all accuracy: 37.60 -> 38.71Improved
Use context to gate image regions (CAI) rather than incorporating it into the query (ablation)TDA frame recognition · imSitu developmentvalue accuracy: 72.96 -> 73.17Improved
Use context to gate image regions (CAI) rather than incorporating it into the query (ablation)TDA frame recognition · imSitu developmentvalue-all accuracy: 37.60 -> 37.95Improved
Add an auxiliary image reconstruction loss (CAIR) (ablation)TDA frame recognition · imSitu developmentvalue accuracy: 72.96 -> 73.30Improved
Add an auxiliary image reconstruction loss (CAIR) (ablation)TDA frame recognition · imSitu developmentvalue-all accuracy: 37.60 -> 38.17Improved
Combine query-context CAQ and image-context CAI (ablation)CAQ frame recognition · imSitu developmentvalue accuracy: 73.62 -> 72.94Hurt
Combine query-context CAQ and image-context CAI (ablation)CAQ frame recognition · imSitu developmentvalue-all accuracy: 38.71 -> 37.38Hurt
Add CAIR to CAQ (ablation)CAQ frame recognition · imSitu developmentvalue accuracy: 73.62 -> 73.62No clear effect
Add CAIR to CAQ (ablation)CAQ frame recognition · imSitu developmentvalue-all accuracy: 38.71 -> 38.63Hurt
Use RE-VGG verb scores alongside CAQCAQ situation recognition · imSitu testtop-1 verb accuracy: 36.97 -> 38.19Improved
Use RE-VGG verb scores alongside CAQCAQ situation recognition · imSitu testtop-1 value accuracy: 29.29 -> 30.23Improved

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