Graph-structured representations for visual question answering

Date

2017

Authors

Teney, D.
Liu, L.
van den Hengel, A.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2017, vol.2017-January, pp.3233-3241

Statement of Responsibility

Damien Teney, Lingqiao Liu, Anton van den Hengel

Conference Name

30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017) (21 Jul 2017 - 26 Jul 2017 : Honolulu, HI)

Abstract

This paper proposes to improve visual question answering (VQA) with structured representations of both scene contents and questions. A key challenge in VQA is to require joint reasoning over the visual and text domains. The predominant CNN/LSTM-based approach to VQA is limited by monolithic vector representations that largely ignore structure in the scene and in the question. CNN feature vectors cannot effectively capture situations as simple as multiple object instances, and LSTMs process questions as series of words, which do not reflect the true complexity of language structure. We instead propose to build graphs over the scene objects and over the question words, and we describe a deep neural network that exploits the structure in these representations. We show that this approach achieves significant improvements over the state-of-the-art, increasing accuracy from 71.2% to 74.4% in accuracy on the abstract scenes multiple-choice benchmark, and from 34.7% to 39.1% in accuracy over pairs of balanced scenes, i.e. images with fine-grained differences and opposite yes/no answers to a same question.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2017 IEEE

License

Grant ID

Call number

Persistent link to this record