AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Commonly Uncommon: Semantic Sparsity in Situation Recognition

Mark Yatskar, Vicente Ordonez, Luke Zettlemoyer, Ali Farhadi

CVPR 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 45 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 tensor composition with image regression potentials (ablation)Image Regression CRF · imSitu developmenttop-5 verb accuracy: 58.64 -> 59.92Improved
Add semantic augmentation to the image regression baseline (ablation)Image Regression CRF · imSitu rare developmenttop-5 verb accuracy: 44.00 -> 43.08Hurt
Add semantic augmentation to tensor composition with regression (ablation)Tensor composition + reg · imSitu developmenttop-5 verb accuracy: 59.92 -> 61.75Improved
Add self-training after semantic augmentation (ablation)Tensor composition + reg + SA · imSitu developmenttop-5 verb accuracy: 61.75 -> 62.21Improved
Add self-training after semantic augmentation (ablation)Tensor composition + reg + SA · imSitu developmentvalue accuracy given ground truth verbs: 35.08 -> 34.82Hurt
Add semantic augmentation to tensor composition with regression (ablation)Tensor composition + reg · imSitu rare developmenttop-5 verb accuracy: 45.14 -> 44.82Improved
Add self-training after semantic augmentation (ablation)Tensor composition + reg + SA · imSitu rare developmenttop-5 verb accuracy: 44.82 -> 45.94Improved
Combine tensor composition, image regression, semantic augmentation, and self-trainingImage Regression CRF · imSitu testtop-5 verb accuracy: 58.88 -> 62.59Improved

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