ML Anthology

Visual Question Answering with Memory-Augmented Networks

Chao Ma, Chunhua Shen, Anthony Dick, Qi Wu, Peng Wang, Anton van den Hengel, Ian Reid
CVPR 2018
doi:10.1109/CVPR.2018.00729 /cvpr/2018/ma2018cvpr-visual/

Abstract

In this paper, we exploit memory-augmented neural networks to predict accurate answers to visual questions, even when those answers rarely occur in the training set. The memory network incorporates both internal and external memory blocks and selectively pays attention to each training exemplar. We show that memory-augmented neural networks are able to maintain a relatively long-term memory of scarce training exemplars, which is important for visual question answering due to the heavy-tailed distribution of answers in a general VQA setting. Experimental results in two large-scale benchmark datasets show the favorable performance of the proposed algorithm with the comparison to state of the art.

PDF CVPR Semantic Scholar

Cite

Text

Ma et al. "Visual Question Answering with Memory-Augmented Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00729

Markdown

[Ma et al. "Visual Question Answering with Memory-Augmented Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/ma2018cvpr-visual/) doi:10.1109/CVPR.2018.00729

BibTeX

@inproceedings{ma2018cvpr-visual,
  title     = {{Visual Question Answering with Memory-Augmented Networks}},
  author    = {Ma, Chao and Shen, Chunhua and Dick, Anthony and Wu, Qi and Wang, Peng and van den Hengel, Anton and Reid, Ian},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00729},
  url       = {https://mlanthology.org/cvpr/2018/ma2018cvpr-visual/}
}