AI Paper Atlas

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

CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning

Kuniaki Saito, Donghyun Kim, Kwanyong Park, Atsushi Hashimoto, Yoshitaka Ushiku

ICCV 2025 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 6 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 descriptiveness control to length control (ablation)CaptionSmiths · MSCOCO (Short)CIDEr: 89.0 -> 98.8Improved
add uniqueness control to length control (ablation)CaptionSmiths · MSCOCO (Short)CIDEr: 89.0 -> 95.1Improved
add uniqueness control on top of length and descriptiveness (ablation)CaptionSmiths · MSCOCO (Short)CIDEr: 98.8 -> 104.8Improved
add descriptiveness control on top of length and uniqueness (ablation)CaptionSmiths · MSCOCO (Short)CIDEr: 95.1 -> 104.8Improved
replace discrete cluster conditioning (5 groups) with continuous interpolation (ablation)CaptionSmiths · COCO (trained on COCO only)CIDEr: 110 -> 112Improved
replace discrete cluster conditioning (100 groups) with continuous interpolation (ablation)CaptionSmiths · COCO (trained on COCO only)CIDEr: 103 -> 112Improved
replace discrete conditioning (5 groups) with continuous interpolation (ablation)CaptionSmiths · COCO (trained on COCO only)length mismatch: 13.8 -> 1.6Improved
increase discrete group count from 5 to 100 (ablation)discrete conditioning · COCO (trained on COCO only)length mismatch and CIDEr: length mismatch 13.8 -> 9.7; CIDEr 110 -> 103Mixed
add descriptiveness and uniqueness conditions to length-only LC baselineCaptionSmiths · COCO (trained on COCO only)CIDEr: 103.6 -> 112.6Improved
add target-caption conditioning to LLaVA trained on mixed dataCaptionSmiths · MSCOCO (Short)CIDEr: 13.2 -> 104.8Improved
use continuous sample-specific conditioning instead of dataset-aware ConcapCaptionSmiths · Docci (Long)CIDEr: 8.3 -> 29.7Improved
use CaptionSmiths instead of Concap on COCOCaptionSmiths · MSCOCO (Short)BLEU@4: 11.5 -> 11.4No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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