AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Cops-Ref: A New Dataset and Task on Compositional Referring Expression Comprehension

Zhenfang Chen, Peng Wang, Lin Ma, Kwan-Yee K. Wong, Qi Wu

CVPR 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Referring expression comprehension · 58 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 modular hard-negative mining (ablation)MattNet · Cops-Ref Fullaccuracy: 26.3 -> 33.8Improved
add modular hard-negative mining (ablation)MattNet · Cops-Ref Cataccuracy: 45.2 -> 54.4Improved
add modular hard-negative mining (ablation)MattNet · Cops-Ref Cat&attraccuracy: 42.5 -> 46.8Improved
add modular hard-negative mining (ablation)MattNet · Cops-Ref Cat&cataccuracy: 45.8 -> 52.0Improved
add modular hard-negative mining (ablation)MattNet · Cops-Ref DiffCataccuracy: 69.1 -> 70.5Improved
add modular hard-negative mining (ablation)MattNet · Cops-Ref WithoutDistaccuracy: 77.9 -> 78.4Improved
use random negatives from the whole dataset (ablation)MattNet · Cops-Ref Fullaccuracy: 26.3 -> 27.6Improved
restrict randomly selected negatives to the same object category (ablation)MattNet · Cops-Ref Cataccuracy: 45.2 -> 53.2Improved
sample negatives by global sentence-feature similarity instead of class-aware random sampling (ablation)MattNet · Cops-Ref Fullaccuracy: 32.2 -> 32.3No clear effect
sample negatives by modular phrase similarity instead of global sentence-feature similarity (ablation)MattNet · Cops-Ref Cat&cataccuracy: 51.2 -> 52.0Improved
add distractor imagesMattNet · Cops-Ref Full versus WithoutDistaccuracy: 77.9 -> 26.3Hurt
mask out the language input (ablation)GroundeR · Cops-Ref Fullaccuracy: 19.1 -> 2.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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