AI Paper Atlas

Research map / Image generation / Editing and style transfer

Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets

Marcella Cornia, Lorenzo Baraldi, Giuseppe Fiameni, Rita Cucchiara

IJCV 2023 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 34 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 web-collected training data (Tiny) (ablation)Ours Tiny · COCO testCIDEr: 139.4 -> 148.4Improved
add web-collected training data (Base) (ablation)Ours Base · nocaps validation overallCIDEr: 89.2 -> 120.5Improved
add retrieval keywords alone (Tiny, no style token) (ablation)Ours Tiny · COCO testCIDEr: 145.8 -> 146.5Improved
add human-annotated style token on top of keywords (Tiny) (ablation)Ours Tiny · COCO testCIDEr: 146.5 -> 148.4Improved
add keywords and style token (Base) (ablation)Ours Base · nocaps validation overallCIDEr: 114.7 -> 120.5Improved
add keywords and style token (Base) (ablation)Ours Base · COCO testCIDEr: 147.9 -> 149.6Improved
retrieval keywords instead of Faster R-CNN tags (Tiny) (ablation)Ours · COCO test (COCO only)CIDEr: 141.1 -> 141.9Improved
retrieval keywords instead of Faster R-CNN tags (Base) (ablation)Ours Base · COCO test (COCO only)CIDEr: 140.5 -> 143.4Improved
condition on human-annotated rather than web-collected style tokenOurs Base · COCO testCIDEr: 86.3 -> 132.3Improved
condition on web-collected rather than human-annotated style tokenOurs Base · CC3M validationCIDEr: 58.8 -> 105.7Improved
scale training images from 5.8M to 35.7MOurs Base · COCO testCIDEr: 147.8 -> 149.6Improved
scale training images from 5.8M to 35.7MOurs Base · nocaps validation overallCIDEr: 118.0 -> 120.5Improved

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