AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Dual Adversarial Graph Neural Networks for Multi-label Cross-modal Retrieval

Shengsheng Qian, Dizhan Xue, Huaiwen Zhang, Quan Fang, Changsheng Xu

AAAI 2021 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 78 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
use DAGNN instead of DSCMRcross-modal retrieval · NUS-WIDEmAP, Average: 0.722 -> 0.757Improved
use DAGNN instead of DSCMRcross-modal retrieval · MIRFlickrmAP, Average: 0.775 -> 0.811Improved
add classification loss Lcla (ablation)DAGNN · NUS-WIDEmAP, Average: 0.520 -> 0.757Improved
add classification loss Lcla (ablation)DAGNN · MIRFlickrmAP, Average: 0.723 -> 0.811Improved
add modality invariance loss Lmdi (ablation)DAGNN · NUS-WIDEmAP, Average: 0.755 -> 0.757Improved
add modality invariance loss Lmdi (ablation)DAGNN · MIRFlickrmAP, Average: 0.807 -> 0.811Improved
add adversarial loss Ladv (ablation)DAGNN · NUS-WIDEmAP, Average: 0.750 -> 0.757Improved
add adversarial loss Ladv (ablation)DAGNN · MIRFlickrmAP, Average: 0.805 -> 0.811Improved
use cross-reconstruction instead of discriminating common image and text representations (ablation)DAGNN · NUS-WIDEmAP, Average: 0.747 -> 0.757Improved
use cross-reconstruction instead of discriminating common image and text representations (ablation)DAGNN · MIRFlickrmAP, Average: 0.802 -> 0.811Improved
use Multi-hop GNN instead of a linear classifier (ablation)DAGNN · NUS-WIDEmAP, Average: 0.734 -> 0.757Improved
use Multi-hop GNN instead of a linear classifier (ablation)DAGNN · MIRFlickrmAP, Average: 0.760 -> 0.811Improved

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