AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Image Captioning and Visual Question Answering Based on Attributes and External Knowledge

Qi Wu, Chunhua Shen, Peng Wang, Anthony Dick, Anton van den Hengel

TPAMI 2017 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 425 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
replace CNN image feature with predicted attribute vector as LSTM inputVggNet+LSTM captioner · MS COCO captioningCIDEr: 0.56 -> 0.94Improved
add region-based attribute prediction instead of global-image prediction (ablation)Att+LSTM captioner · MS COCO captioningCIDEr: 0.83 -> 0.94Improved
add region CNN attribute prediction instead of linear SVM (ablation)Att+LSTM captioner · MS COCO captioningCIDEr: 0.82 -> 0.94Improved
use attributes instead of fine-tuned VggNet featuresVggNet+ft+LSTM · MS COCO captioningCIDEr: 0.73 -> 0.94Improved
add ground-truth attributes (oracle) (ablation)Att+LSTM captioner · MS COCO captioningCIDEr: 0.94 -> 1.07Improved
add image caption representation to attributes (ablation)Att-LSTM · VQA validationoverall accuracy %: 51.60 -> 55.04Improved
add external knowledge to attributes (ablation)Att-LSTM · VQA validationoverall accuracy %: 51.60 -> 53.79Improved
add external knowledge to attributes and captions (ablation)Att+Cap-LSTM · VQA validationoverall accuracy %: 55.04 -> 55.96Improved
select knowledge guided by the question (ablation)Att+Cap+Know-LSTM · VQA validationoverall accuracy %: 55.96 -> 56.17Improved
add external knowledge on why questions (ablation)Att-LSTM · VQA validation, why questionsaccuracy %: 7.77 -> 11.88Improved
add question-selected knowledge on why questions (ablation)A+C+K-LSTM · VQA validation, why questionsaccuracy %: 13.53 -> 13.76Improved
add question-selected knowledge on Toronto COCO-QA (ablation)Att+Cap+Know-LSTM · Toronto COCO-QAaccuracy %: 69.73 -> 70.98Improved

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