AI Paper Atlas

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

Relationship-Embedded Representation Learning for Grounding Referring Expressions

Sibei Yang, Guanbin Li, Yizhou Yu

TPAMI 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Referring expression comprehension · 77 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 language-guided visual context (guided viscxt) instead of global visual context (ablation)CMRIN · RefCOCOg testPrecision@1: 75.23 -> 78.29Improved
add global graph visual context over instance-only baseline (ablation)CMRIN · RefCOCOg testPrecision@1: 71.26 -> 75.23Improved
fuse word context into the language-guided graph (multimodal fusion) (ablation)CMRIN · RefCOCOg testPrecision@1: 78.29 -> 80.85Improved
use 2 gated graph conv layers instead of 1 (ablation)CMRIN · RefCOCOg testPrecision@1: 79.38 -> 80.85Improved
use 3 gated graph conv layers instead of 2 (ablation)CMRIN · RefCOCOg testPrecision@1: 80.85 -> 80.55No clear effect
train with triplet loss with hard negative mining instead of softmax loss (ablation)CMRIN · RefCOCOg testPrecision@1: 79.37 -> 80.85Improved
use margin 0.5 instead of 0.1 in triplet loss (ablation)CMRIN · RefCOCO+ valPrecision@1: 75.63 -> 74.52Hurt
vary negative sampling strategy (hardest, semi-hard, two negatives) (ablation)CMRIN · RefCOCO valPrecision@1: 86.43 -> 86.38No clear effect
add explicit noun phrases for vertex highlighting (ablation)CMRIN · RefCOCO+ testBPrecision@1: 68.23 -> 69.58Improved
use 11 edge types instead of 7 types (ablation)CMRIN · RefCOCO testBPrecision@1: 84.26 -> 85.52Improved
connect pairs by center distance 0.7 instead of 0.5 (ablation)CMRIN · RefCOCOg testPrecision@1: 80.85 -> 80.20Hurt
add semantic relation graph branch to spatial branch (ablation)CMRIN · RefCOCO testAPrecision@1: 87.36 -> 88.17Improved

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