AI Paper Atlas

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

Good News, Everyone! Context Driven Entity-Aware Captioning for News Images

Ali Furkan Biten, Lluis Gomez, Marcal Rusinol, Dimosthenis Karatzas

CVPR 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Concept-guided image captioning · 139 citations (OpenAlex)

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 article context with sentence-level average encodingShow Attend Tell captioning pipeline · GoodNewsCIDEr: 12.15% -> 12.75%Improved
Add named-entity insertion rather than omit entities (ablation)Show Attend Tell · GoodNewsCIDEr: 1.67% -> 10.03%Improved
Use context-based entity insertion instead of random insertion (ablation)Show Attend Tell · GoodNewsCIDEr: 10.03% -> 12.15%Improved
Use attention-guided entity insertion instead of context-based insertion (ablation)Ours (Avg.) · GoodNewsexact-match entity precision: 8.17 -> 9.19Improved
Use attention-guided entity insertion instead of context-based insertion (ablation)Ours (Avg.) · GoodNewsCIDEr: 12.75% -> 12.70%No clear effect
Use simple average rather than weighted-average article encoding (ablation)Ours + CtxIns · GoodNews template captionsCIDEr: 17.132% -> 17.577%Improved
Use simple average rather than TBB article encoding (ablation)Ours + CtxIns · GoodNews template captionsCIDEr: 16.624% -> 17.577%Improved
Use attention-guided entity insertion rather than context-based insertion (ablation)Ours (Avg.) · GoodNewspartial-match entity recall: 17.88 -> 19.48Improved
Use average article encoding rather than weighted average (ablation)Ours + CtxIns · GoodNewsCIDEr: 12.37% -> 12.75%Improved
Use average article encoding rather than TBB (ablation)Ours + CtxIns · GoodNewsCIDEr: 12.70% -> 12.75%No clear effect
Use visual and textual context rather than visual-only captioningShow Attend Tell + CtxIns · GoodNewsCIDEr: 12.15% -> 12.75%Improved
Use the proposed visual-plus-textual model rather than Show Attend Tell + CtxInsGoodNews captioning · GoodNews human evaluationpreference rate: 53%Improved

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