AI Paper Atlas

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

Attention on Attention for Image Captioning

Lun Huang, Wenmin Wang, Jie Chen, Xiao-Yong Wei

ICCV 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 1,117 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 refining module without AoA to encoder (ablation)Base · MS-COCO Karpathy (XE)CIDEr-D: 109.5 -> 112.5Improved
add AoA to the encoder refining module (ablation)Base + refining module · MS-COCO Karpathy (XE)CIDEr-D: 112.5 -> 114.5Improved
model decoder context vector with LSTM (ablation)Base · MS-COCO Karpathy (XE)CIDEr-D: 109.5 -> 113.5Improved
model decoder context vector with AoA instead of linear transform (ablation)Base · MS-COCO Karpathy (XE)CIDEr-D: 109.5 -> 113.8Improved
replace LSTM context with AoA (ablation)Decoder · MS-COCO Karpathy (XE)CIDEr-D: 113.5 -> 113.8Improved
stack AoA on top of LSTM (ablation)Decoder · MS-COCO Karpathy (XE)CIDEr-D: unstable training processHurt
use multi-head attention in decoder instead of single attention (ablation)Base decoder · MS-COCO Karpathy (XE)CIDEr-D: 109.5 -> 109.6No clear effect
add AoA to multi-head attention decoder (ablation)Decoder with MH-Att · MS-COCO Karpathy (XE)CIDEr-D: 109.6 -> 114.3Improved
add AoA to multi-head attention decoder with LSTM (ablation)Decoder · MS-COCO Karpathy (XE)CIDEr-D: 113.8 -> 114.3Improved
combine AoA in both encoder and decoder (full AoANet) (ablation)Base · MS-COCO Karpathy (XE)CIDEr-D: 109.5 -> 119.8Improved
use decoder with AoA in video captioningBase decoder · MSR-VTTCIDEr-D: 38.83 -> 42.44Improved
use decoder with AoA in video captioningBase decoder · MSR-VTTBLEU-4: 33.53 -> 37.22Improved

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