AI Paper Atlas

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

Ask Your Neurons: A Deep Learning Approach to Visual Question Answering

Mateusz Malinowski, Marcus Rohrbach, Mario Fritz

IJCV 2017 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 112 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
train to predict only a single word answerAsk Your Neurons · DAQUAR (all classes)accuracy: 17.49 -> 19.43Improved
add visual input to question-only model (ablation)Ask Your Neurons (single word) · DAQUAR (all classes)accuracy: 17.15 -> 19.43Improved
add visual input to question-only model (ablation)Ask Your Neurons · DAQUAR (reduced)accuracy: 32.32 -> 34.68Improved
use refined model with GLOVE and ResNet-152Ask Your Neurons · DAQUAR (all)accuracy: 19.43 -> 24.48Improved
add box filter smoothing of validation accuracyRefined Ask Your Neurons · DAQUAR (all)accuracy: 24.48 -> 25.74Improved
add GLOVE pre-trained word embedding (ablation)LSTM question-only · VQA validationaccuracy: 47.80 -> 48.58Improved
restrict answers to the top 2000 most frequent (ablation)LSTM question-only · VQA validationaccuracy: 48.58 -> 48.86Improved
add L2 normalisation of visual features (ablation)Summation fusion · VQA validationaccuracy: 40.67 -> 53.27Improved
add L2 normalisation of visual features (ablation)Concatenation fusion · VQA validationaccuracy: 47.21 -> 52.39Improved
add L2 normalisation of visual features (ablation)Element-wise multiplication fusion · VQA validationaccuracy: 49.50 -> 52.70Improved
use ResNet-152 instead of AlexNet visual encoderLSTM + GLOVE · VQA validationaccuracy: 53.69 -> 55.52Improved
use LSTM instead of BOW question encodervision and language model · VQA validationaccuracy: 53.27 -> 54.29Improved

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