AI Paper Atlas

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

Image Enhanced Event Detection in News Articles

Meihan Tong, Shuai Wang, Yixin Cao, Bin Xu, Juanzi Li, Lei Hou, Tat-Seng Chua

AAAI 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal retrieval-augmented modeling · 46 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 images with dual recurrent multimodal model (DRMM) on top of BERT (ablation)BERT · ACE2005 EDF1: 75.1 -> 76.3Improved
add image modality (ablation)CNN encoder · ACE2005 EDF1: 59.9 -> 63.3Improved
add image modality (ablation)LSTM encoder · ACE2005 EDF1: 60.2 -> 64.8Improved
use alternating dual attention instead of concatenation fusion (ablation)DRMM · ACE2005 EDF1: 69.2 -> 76.3Improved
use alternating dual attention instead of modality attention (ablation)DRMM · ACE2005 EDF1: 73.8 -> 76.3Improved
use alternating dual attention instead of co-attention (ablation)DRMM · ACE2005 EDF1: 74.6 -> 76.3Improved
add images to masked language model (ablation)language model · ACE2005 MLMF1: 75.8 -> 79.4Improved
add image modality (BERT+image) for zero-shot and few-shot triggers (ablation)BERT · ACE2005 ED, trigger frequency bucketsPrecision: +3.9% zero-shot, +2.7% few-shotImproved
add image modality (BERT+image) for high-frequency triggers (ablation)BERT · ACE2005 ED, high-frequency triggersPrecision: -0.7%No clear effect
DRMM (BERT+images) vs text-only AD-DMBERTevent detection · ACE2005 EDF1: 75.1 -> 76.3Improved

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