AI Paper Atlas

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

Areas of Attention for Image Captioning

Marco Pedersoli, Thomas Lucas, Cordelia Schmid, Jakob Verbeek

ICCV 2017 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 212 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 word-region interaction term (ablation)captioning baseline, activation grid · MSCOCOCIDEr: 78.9 -> 83.6Improved
add region-state interaction term (ablation)attention model, activation grid · MSCOCOCIDEr: 83.6 -> 85.5Improved
add visual feedback in the RNN state update (ablation)attention model, activation grid · MSCOCOCIDEr: 85.5 -> 87.4Improved
use word-conditional feedback instead of marginal feedback (ablation)attention model, activation grid · MSCOCOCIDEr: 87.4 -> 86.8Hurt
replace activation grid with spatial transformer regions (RNN training only)attention model · MSCOCOCIDEr: 87.4 -> 91.1Improved
replace object proposals with spatial transformer regions (RNN training only)attention model · MSCOCOCIDEr: 89.0 -> 91.1Improved
replace activation grid with object proposals (RNN training only)attention model · MSCOCOCIDEr: 87.4 -> 89.0Improved
add joint CNN-RNN fine-tuning (ablation)attention model, spatial transformers · MSCOCOCIDEr: 91.1 -> 93.8Improved
add joint CNN-RNN fine-tuning (ablation)baseline captioning model · MSCOCOCIDEr: 78.9 -> 87.1Improved
replace object proposals with spatial transformers after fine-tuningattention model · MSCOCOCIDEr: 93.7 -> 93.8No clear effect
replace activation grid with spatial transformers after fine-tuningattention model · MSCOCOCIDEr: 92.6 -> 93.8Improved
use four or fewer test-time regionsattention model · MSCOCOCIDErHurt

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