AI Paper Atlas

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

Towards Unique and Informative Captioning of Images

Zeyu Wang, Berthy Feng, Karthik Narasimhan, Olga Russakovsky

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 30 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 interpolated LM mutual-information re-rankingTopDown · COCO testSPICE-U: 23.70 -> 25.27Improved
add interpolated LM mutual-information re-rankingTopDown · COCO testGeoMean: 12.63 -> 12.94Improved
add interpolated LM mutual-information re-rankingDiscCap · COCO testSPICE-U: 23.74 -> 24.52Improved
add interpolated LM mutual-information re-rankingAoANet · COCO testSPICE-U: 26.04 -> 26.53Improved
add interpolated LM mutual-information re-rankingTopDown · COCO testCHAIRs: 8.68 -> 7.80Improved
add interpolated LM mutual-information re-rankingTopDown · COCO testCIDEr: 108.13 -> 106.42Hurt
add interpolated LM mutual-information re-rankingDiscCap · COCO testCIDEr: 112.39 -> 110.90Hurt
add interpolated LM mutual-information re-rankingAoANet · COCO testBLEU: 27.53 -> 27.18Hurt
use unigram LM instead of LSTM LM for re-ranking (ablation)TopDown · COCO testSPICE-U: 24.46 -> 25.05Improved
use LSTM LM instead of interpolated LM for re-ranking (ablation)AoANet · COCO testSPICE-U: 26.12 -> 26.53Improved
use LSTM LM only for re-ranking (ablation)DiscCap · COCO testSPICE-U: 23.74 -> 23.79No clear effect
use SPICE-U instead of SPICE as metricPASCAL-50S · PASCAL-50SPearson correlation: 0.749 -> 0.767Improved

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