AI Paper Atlas

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

Aesthetically Relevant Image Captioning

Zhipeng Zhong, Fei Zhou, Guoping Qiu

AAAI 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 15 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
Weight caption training loss by sentence ARS rather than using standard cross-entropy (ablation)VisualGPT image aesthetic captioning on DPC2022 · DPC2022 image aesthetic captioningSPICE: 0.0172 -> 0.0353Improved
Weight caption training loss by sentence ARS rather than using standard cross-entropy (ablation)VisualGPT image aesthetic captioning on DPC2022 · DPC2022 image aesthetic captioningMETETOR: 0.1227 -> 0.1389Improved
Select generated captions with ARS-based DACS instead of using captions without aesthetic selection (ablation)Generated-caption text-only AQA · DPC2022 generated-caption text-only AQASRCC: 0.4335 -> 0.4711Improved
Select generated captions with CLIP-based DACS instead of using captions without aesthetic selection (ablation)Generated-caption text-only AQA · DPC2022 generated-caption text-only AQASRCC: 0.4335 -> 0.476Improved
Use ARS-selected captions instead of unselected generated captions (ablation)Generated-caption multi-modal AQA · DPC2022 generated-caption multi-modal AQAMAE: 0.4232 -> 0.4192Improved
Use CLIP-selected captions instead of unselected generated captions (ablation)Generated-caption multi-modal AQA · DPC2022 generated-caption multi-modal AQAMAE: 0.4232 -> 0.4179Improved
Use captions selected by DACS instead of generator-confidence captions (ablation)Generated-caption multi-modal AQA · DPC2022 generated-caption multi-modal AQAACC: 0.8181 -> 0.8203Improved
Use higher-ARS comments rather than lower-ARS comments (ablation)ViT+BERT multi-modal AQA · DPC2022 multi-modal AQASRCC: 0.8216 -> 0.9157Improved
Use higher-ARS comments rather than lower-ARS comments (ablation)ViT+BERT multi-modal AQA · DPC2022 multi-modal AQAACC: 0.8486 -> 0.8991Improved
Use generated captions rather than ground-truth text (ablation)Text-only AQA · DPC2022 text-only AQASRCC: 0.8274 -> 0.476Hurt

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