AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

VrR-VG: Refocusing Visually-Relevant Relationships

Yuanzhi Liang, Yalong Bai, Wei Zhang, Xueming Qian, Li Zhu, Tao Mei

ICCV 2019 · Vision-language and multimodal › Visual question answering · approach: Vision-language model VQA evaluation · 83 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 relation supervision (relation loss and relation data) to feature learning (ablation)Ours features on VrR-VG, MUTAN · VQA-2.0 valaccuracy (All): 62.93 -> 64.57Improved
add relation supervision (relation loss and relation data) to feature learning (ablation)Ours features on VrR-VG, MFH · VQA-2.0 valaccuracy (All): 64.68 -> 65.46Improved
filter visually-irrelevant relationships with VD-Net (R-VG to VrR-VG) (ablation)Ours features, MUTAN · VQA-2.0 valaccuracy (All): 63.77 -> 64.57Improved
filter visually-irrelevant relationships with VD-Net (R-VG to VrR-VG) (ablation)Ours features, MFH · VQA-2.0 valaccuracy (All): 64.22 -> 65.46Improved
train relation-aware features on VrR-VG instead of VG150Ours features, MUTAN · VQA-2.0 valaccuracy (All): 59.49 -> 64.57Improved
add relation supervision to feature learning (ablation)Ours features on VrR-VG · MSCOCO 2014 captioning (cross-entropy loss)CIDEr: 110.3 -> 114.0Improved
add relation supervision to feature learning (ablation)Ours features on VrR-VG · MSCOCO 2014 captioning (CIDEr optimization)CIDEr: 116.8 -> 120.7Improved
filter visually-irrelevant relationships with VD-Net (R-VG to VrR-VG) (ablation)Ours features · MSCOCO 2014 captioning (cross-entropy loss)CIDEr: 111.2 -> 114.0Improved
train relation-aware features on VrR-VG instead of VG150Ours features · MSCOCO 2014 captioning (CIDEr optimization)CIDEr: 108.0 -> 120.7Improved
use relation-aware VrR-VG features instead of BottomUp object-attribute features on larger BottomUp-VGMUTAN VQA · VQA-2.0 valaccuracy (All): 62.84 -> 64.57Improved
switch dataset from VG150 to VrR-VG for the frequency baselineFrequency-Baseline · PredDetR@50: 94.6 -> 69.8Hurt
switch dataset from VG150 to VrR-VG for a learnable methodNeural-Motifs · PredDetR@50: 96.0 -> 87.6Hurt

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