AI Paper Atlas

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

DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue

Xiaoze Jiang, Jing Yu, Zengchang Qin, Yingying Zhuang, Xingxing Zhang, Yue Hu, Qi Wu

AAAI 2020 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 70 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
combine appearance-level visual features with semantic captions using adaptive fusion (ablation)DualVD · VisDial v1.0 validationMRR: 61.07 -> 64.64Improved
add relational semantics to object and neighborhood features (ablation)DualVD visual module · VisDial v1.0 validationMRR: 63.97 -> 64.11Improved
combine object appearance with relation-aware object features (ablation)DualVD visual module · VisDial v1.0 validationMRR: 63.84 -> 64.11Improved
use relationally enhanced object representations instead of object features alone (ablation)DualVD visual module · VisDial v1.0 validationMRR: 63.84 -> 64.11Improved
fuse global and local caption information instead of using either alone (ablation)DualVD semantic module · VisDial v1.0 validationMRR: 60.02 -> 61.07; 60.95 -> 61.07Improved
add ELMo word embeddings (ablation)DualVD · VisDial v1.0 validationMRR: 63.67 -> 64.64Improved
strengthen relational features while weakening object appearance (ablation)DualVD visual representation · VisDial v1.0 validationMRR: 63.63 vs 64.11Hurt
use global and local captions together rather than global captions alone (ablation)DualVD semantic module · VisDial v1.0 validationMRR: 60.02 -> 61.07Improved
use global and local captions together rather than local captions alone (ablation)DualVD semantic module · VisDial v1.0 validationMRR: 60.95 -> 61.07Improved
use DualVD rather than RvAVisDial v1.0 · test-standardMRR: 63.03 -> 63.23Improved
use DualVD rather than DL-61VisDial v1.0 · test-standardNDCG: 57.32 -> 56.32Hurt

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