AI Paper Atlas

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

Linguistic Structure Guided Context Modeling for Referring Image Segmentation

Tianrui Hui, Si Liu, Shaofei Huang, Guanbin Li, Sansi Yu, Faxi Zhang, Jizhong Han

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Referring expression comprehension · 201 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 LSCM module (ablation)RRN-CNN single-level · UNC valOverall IoU (%): 47.26 -> 54.87Improved
add LSCM module (ablation)Multi-Level-RRN-CNN · UNC valOverall IoU (%): 57.61 -> 59.67Improved
add GloVe embeddings (ablation)LSCM single-level · UNC valOverall IoU (%): 54.87 -> 55.93Improved
add Mutan fusion (ablation)LSCM + GloVe single-level · UNC valOverall IoU (%): 55.93 -> 56.50Improved
add GloVe embeddings (ablation)LSCM multi-level · UNC valOverall IoU (%): 59.67 -> 60.98Improved
add Dual-Path Fusion instead of Concat Fusion (ablation)LSCM multi-level · UNC valOverall IoU (%): 60.10 -> 61.54Improved
add Dual-Path Fusion instead of Gated Fusion (ablation)LSCM multi-level · UNC valOverall IoU (%): 60.46 -> 61.54Improved
use LSCM instead of GloRe (ablation)multi-level baseline · UNC valOverall IoU (%): 58.53 -> 59.67Improved
use 1 graph conv layer instead of 0 (ablation)LSCM + GloVe · UNC valOverall IoU (%): 54.51 -> 55.93Improved
increase graph conv layers from 1 to 2 (ablation)LSCM + GloVe · UNC valOverall IoU (%): 55.93 -> 50.77Hurt
use adaptive layers equal to DPT depth instead of 1 (ablation)LSCM + GloVe · UNC valOverall IoU (%): 55.93 -> 54.69Hurt
increase graph conv layers from 1 to 2 (ablation)LSCM + GloVe · G-Ref valOverall IoU (%): 40.54 -> 39.29Hurt

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