AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Modeling Context Between Objects for Referring Expression Understanding

Varun K. Nagaraja, Vlad I. Morariu, Larry S. Davis

ECCV 2016 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 472 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
train with MIL negative bag margin loss instead of max-marginreferring expression LSTM · Google RefExp Val (GT proposals)Precision@1: 65.7 -> 68.4Improved
train with MIL negative bag margin loss instead of max-marginreferring expression LSTM · UNC RefExp Val (GT proposals)Precision@1: 74.4 -> 76.9Improved
train with MIL negative bag margin loss instead of max-marginreferring expression LSTM · UNC RefExp TestB (MCG proposals)Precision@1: 55.1 -> 56.4Improved
train with MIL negative bag margin loss instead of max-marginreferring expression LSTM · UNC RefExp TestA (MCG proposals)Precision@1: 58.4 -> 58.6No clear effect
add positive bag margin to negative bag marginMIL loss · Google RefExp Val (MCG proposals)Precision@1: 49.5 -> 50.0Improved
add positive bag margin to negative bag marginMIL loss · UNC RefExp Val (GT proposals)Precision@1: 76.9 -> 76.1Hurt
pool context with noisy-or instead of max (ablation)MIL negative bag margin · Google RefExp Val (GT proposals)Precision@1: 66.5 -> 68.4Improved
pool context over all regions with noisy-or instead of image only (ablation)MIL negative bag margin · Google RefExp Val (GT proposals)Precision@1: 65.9 -> 68.4Improved
pool context over all regions with noisy-or instead of image only (ablation)MIL negative bag margin · UNC RefExp Val (GT proposals)Precision@1: 76.4 -> 76.9Improved
pool context over all regions with noisy-or instead of image only (ablation)MIL negative bag margin · UNC RefExp TestA (GT proposals)Precision@1: 76.2 -> 75.6Hurt
train with MIL loss using image-only context instead of max-marginreferring expression LSTM · Google RefExp Val (GT proposals)Precision@1: 65.7 -> 65.9Improved
use ground-truth proposals instead of MCG proposalsOurs, Pos. & Neg. Bag Mgn. · Google RefExp ValPrecision@1: 50.0 -> 68.4Improved

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