AI Paper Atlas

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

Exploring Overall Contextual Information for Image Captioning in Human-Like Cognitive Style

Hongwei Ge, Zehang Yan, Kai Zhang, Mingde Zhao, Liang Sun

ICCV 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 24 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 mutual-aid auxiliary structure (lambda 0.01) (ablation)forward LSTM L_f · MS COCO Karpathy test (frozen encoder)CIDEr: 99.9 -> 105.7Improved
add mutual-aid auxiliary structure (lambda 0.01) (ablation)backward LSTM L_b · MS COCO Karpathy test (frozen encoder)CIDEr: 99.7 -> 103.6Improved
add mutual-aid auxiliary structure (lambda 0.01) (ablation)forward LSTM L_f · MS COCO Karpathy test (frozen encoder)BLEU-4: 32.1 -> 33.5Improved
add mutual-aid auxiliary structure (lambda 0.01) (ablation)backward LSTM L_b · MS COCO Karpathy test (frozen encoder)BLEU-4: 31.0 -> 31.9Improved
raise lambda from 0.01 to 0.1 (ablation)forward LSTM L_f · MS COCO Karpathy test (frozen encoder)CIDEr: 105.7 -> 100.0Hurt
raise lambda from 0.01 to 0.1 (ablation)backward LSTM L_b · MS COCO Karpathy test (frozen encoder)CIDEr: 103.6 -> 99.5Hurt
lambda 0.1 versus no auxiliary structure (ablation)forward LSTM L_f · MS COCO Karpathy test (frozen encoder)CIDEr: 99.9 -> 100.0No clear effect
use forward instead of backward generationMaBi-LSTMs · MS COCO Karpathy testCIDEr: 108.5 -> 110.4Improved
add cross-modal attention over image and pre-generated sentences (ablation)MaBi-LSTMs L_f · MS COCO Karpathy testCIDEr: 110.4 -> 116.6Improved
add cross-modal attention over image and pre-generated sentences (ablation)MaBi-LSTMs L_f · MS COCO Karpathy testBLEU-4: 36.4 -> 36.8Improved
add cross-modal attention (vs L_b captions) (ablation)MaBi-LSTMs L_b · MS COCO Karpathy testCIDEr: 108.5 -> 116.6Improved
fine-tune encoder jointly with decoderMaBi-LSTMs · MS COCO Karpathy testCIDEr: 105.7 -> 110.4Improved

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