AI Paper Atlas

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

Referring Image Segmentation via Cross-Modal Progressive Comprehension

Shaofei Huang, Tianrui Hui, Si Liu, Guanbin Li, Yunchao Wei, Jizhong Han, Luoqi Liu, Bo Li

CVPR 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Referring expression comprehension · 236 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 entity perception (EP) to the baseline (ablation)CMPC-Refseg · UNC valOverall IoU: 47.36 -> 49.06Improved
Add relation-aware reasoning (RAR) to the baseline (ablation)CMPC-Refseg · UNC valOverall IoU: 47.36 -> 53.40Improved
Add EP and RAR together (ablation)CMPC-Refseg · UNC valOverall IoU: 47.36 -> 55.38Improved
Initialize word embeddings with GloVe (ablation)EP + RAR · UNC valOverall IoU: 55.38 -> 56.00Improved
Add TGFE to a multi-level baseline (ablation)CMPC-Refseg · UNC valOverall IoU: 56.38 -> 58.81Improved
Add EP and RAR to the multi-level TGFE model (ablation)CMPC-Refseg · UNC valOverall IoU: 58.81 -> 60.72Improved
Increase TGFE exchange rounds from one to three (ablation)CMPC-Refseg · UNC valOverall IoU: 60.72 -> 61.25Improved
Use three graph convolution layers instead of one (ablation)CMPC-Refseg · UNC valOverall IoU: 55.38 -> 50.70Hurt
Use two graph convolution layers instead of one (ablation)CMPC-Refseg · G-Ref valOverall IoU: 38.19 -> 40.12Improved
Use three graph convolution layers instead of two (ablation)CMPC-Refseg · G-Ref valOverall IoU: 40.12 -> 38.96Hurt
Use CMPC-Refseg instead of STEPReferring segmentation benchmarks · UNC valOverall IoU: 60.04 -> 61.36Improved
Use CMPC-Refseg instead of STEPReferring segmentation benchmarks · UNC testAOverall IoU: 63.46 -> 64.53Improved

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