AI Paper Atlas

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

An Empirical Study of Language CNN for Image Captioning

Jiuxiang Gu, Gang Wang, Jianfei Cai, Tsuhan Chen

ICCV 2017 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 160 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 language CNN to simple RNNSimple RNN · MS COCOCIDEr: 87.0 -> 95.2Improved
add language CNN to RHNRHN · MS COCOCIDEr: 90.6 -> 98.9Improved
add language CNN to LSTMLSTM · MS COCOCIDEr: 92.6 -> 99.1Improved
add language CNN to GRUGRU · MS COCOCIDEr: 93.3 -> 96.1Improved
add language CNN to LSTMLSTM · Flickr30kCIDEr: 35.0 -> 45.0Improved
add language CNN to RHNRHN · Flickr30kBLEU-4: 20.0 -> 30.7Improved
add language CNN to simple RNNSimple RNN · Flickr30kCIDEr: 32.5 -> 65.4Improved
add a 2nd LSTM layer instead of a language CNN (ablation)LSTM · MS COCOCIDEr: 92.6 -> 93.2Improved
add a 3rd LSTM layer (ablation)LSTM · MS COCOCIDEr: 92.6 -> 92.9No clear effect
add RNN on top of the language CNN (ablation)CNN_L · MS COCOCIDEr: 56.8 -> 95.2Improved
use a larger window of previous words (2 -> 8 words) (ablation)CNN_L+RHN · MS COCOCIDEr: 93.8 -> 95.9Improved
use full 16-word language CNN rather than 8 words (ablation)CNN_L+RHN · MS COCOCIDEr: 95.9 -> 98.9Improved

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