NeurIPS 2018poster294 citations

Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering

Medhini Narasimhan, Svetlana Lazebnik, Alexander Schwing

Abstract

Accurately answering a question about a given image requires combining observations with general knowledge. While this is effortless for humans, reasoning with general knowledge remains an algorithmic challenge. To advance research in this direction a novel

BibTeX
@inproceedings{NEURIPS2018_c26820b8,
 author = {Narasimhan, Medhini and Lazebnik, Svetlana and Schwing, Alexander},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering},
 url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/c26820b8a4c1b3c2aa868d6d57e14a79-Paper.pdf},
 volume = {31},
 year = {2018}
}
Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering · NeurIPS 2018