AI Paper Atlas

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

Boosting Image Captioning With Attributes

Ting Yao, Yingwei Pan, Yehao Li, Zhaofan Qiu, Tao Mei

ICCV 2017 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 760 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
feed attributes instead of image representations onlyLSTM · COCO Karpathy test (GoogleNet)CIDEr-D: 84.3 -> 96Improved
add attributes after image representations (A2 vs A1) (ablation)LSTM-A1 · COCO Karpathy test (GoogleNet)CIDEr-D: 96 -> 97.5Improved
feed attributes first, then image representations (A3 vs A2) (ablation)LSTM-A2 · COCO Karpathy test (GoogleNet)CIDEr-D: 97.5 -> 98.4Improved
input image representations at each time step (A4 vs A3) (ablation)LSTM-A3 · COCO Karpathy test (GoogleNet)CIDEr-D: 98.4 -> 90.6Hurt
input attributes at each time step (A5 vs A3) (ablation)LSTM-A3 · COCO Karpathy test (GoogleNet)CIDEr-D: 98.4 -> 98.6Improved
input attributes at each time step (A5 vs A3) (ablation)LSTM-A3 · COCO Karpathy test (GoogleNet)BLEU@4: 32.1 -> 32.5Improved
input image representations at each time step (A4 vs A3) (ablation)LSTM-A3 · COCO Karpathy test (GoogleNet)BLEU@4: 32.1 -> 30.6Hurt
add attributes as auxiliary input in LSTM-A5 vs ATT semantic attentionATT · COCO Karpathy test (GoogleNet)BLEU@4: 30.4 -> 32.5Improved
add attributes to LRCN-style per-step image input (A4 vs LRCN)LRCN · COCO Karpathy test (GoogleNet)BLEU@4: 21 -> 30.6Improved
train attribute detectors with ResNet-152 instead of GoogleNetLSTM-A3 · COCO Karpathy test (GoogleNet)CIDEr-D: 98.4 -> 104.9Improved
vary beam size k from 1 to 5 (ablation)LSTM-A3 / LSTM-A5 · COCO Karpathy test (GoogleNet)CIDEr-DMixed

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