AI Paper Atlas

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

Towards Accurate Text-Based Image Captioning With Content Diversity Exploration

Guanghui Xu, Shuaicheng Niu, Mingkui Tan, Yucheng Luo, Qing Du, Qi Wu

CVPR 2021 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 62 citations (OpenAlex)

Check 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 Anchor-Captioner’s anchor selection, ACGs, and text-specific refinementText-based image captioning · TextCaps validation setCIDEr: 89.6 to 95.5Improved
Generate multiple ACG-guided captions rather than beam-search captionsText-based image captioning · TextCaps validation setCover Ratio: 27.3 to 37.8Improved
Use RNN sequence projection rather than independent FC projection for ACG construction (ablation)Anchor-Captioner · TextCaps validation setCIDEr: 90.3 to 95.5Improved
Use RNN sequence projection rather than Transformer multiple projection for ACG construction (ablation)Anchor-Captioner · TextCaps validation setCIDEr: 90.7 to 95.5Improved
Use learned AnPM graph construction rather than rule-based anchor and grouping heuristics (ablation)Anchor-Captioner · TextCaps validation setCIDEr: 78.0 to 95.5Improved
Use ground-truth ACGs instead of predicted ACGs (ablation)Anchor-Captioner · TextCaps validation setCIDEr: 95.5 to 104.9Improved
Add ACG guidance to M4C-Captioner (ablation)M4C-Captioner · TextCaps validation setCIDEr: 89.6 to 93.8Improved
Use ground-truth ACGs rather than predicted ACGs with M4C-Captioner (ablation)M4C-Captioner · TextCaps validation setCIDEr: 93.8 to 99.6Improved
Train jointly on COCO and TextCaps rather than only COCO (ablation)Anchor-Captioner · COCO validationCIDEr: 110.3 to 96.3Hurt
Train jointly on COCO and TextCaps rather than only TextCaps (ablation)Anchor-Captioner · TextCaps validationCIDEr: 95.5 to 90.0Hurt

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