Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Graph-structured representations for visual question answering|
van den Hengel, A.
|Citation:||Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), 2017 / vol.2017-January, pp.3233-3241|
|Series/Report no.:||IEEE Conference on Computer Vision and Pattern Recognition|
|Conference Name:||30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017) (21 Jul 2017 - 26 Jul 2017 : Honolulu, HI)|
|Damien Teney, Lingqiao Liu, Anton van den Hengel|
|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.|
|Rights:||© 2017 IEEE|
|Appears in Collections:||Computer Science publications|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.