Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering

@inproceedings{Xu2016AskAA,
  title={Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering},
  author={Huijuan Xu and Kate Saenko},
  booktitle={ECCV},
  year={2016}
}

• Huijuan Xu, Kate Saenko
• Published 2016 in ECCV
• DOI:10.1007/978-3-319-46478-7_28

The problem of Visual Question Answering (VQA) requires joint image and language understanding to answer a question about a given photograph. Recent approaches have applied deep image captioning methods based on recurrent LSTM networks to this problem, but have failed to model spatial inference. In this paper, we propose a memory network with spatial attention for the VQA task. Memory networks are recurrent neural networks with an explicit attention mechanism that selects certain parts of the… CONTINUE READING

Save to Library

Create Alert

Cite

View on ArXiv