Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/120067
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Are you talking to me? Reasoned visual dialog generation through adversarial learning
Author: Wu, Q.
Wang, P.
Shen, C.
Reid, I.
Hengel, A.
Citation: Proceedings: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018)), 2018 / pp.6106-6115
Publisher: IEEE
Issue Date: 2018
Series/Report no.: IEEE Conference on Computer Vision and Pattern Recognition
ISBN: 9781538664209
ISSN: 1063-6919
2575-7075
Conference Name: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (18 Jun 2018 - 23 Jun 2018 : Salt Lake City, UT)
Statement of
Responsibility: 
Qi Wu, Peng Wang, Chunhua Shen, Ian Reid, Anton van den Hengel
Abstract: The visual dialog task requires an agent to engage in a conversation about an image with a human. It represents an extension of the visual question answering task in that the agent needs to answer a question about an image, but it needs to do so in light of the previous dialog that has taken place. The key challenge in visual dialog is thus maintaining a consistent, and natural dialog while continuing to answer questions correctly. We present a novel approach that combines Reinforcement Learning and Generative Adversarial Networks (GANS) to generate more human-like responses to questions. The GAN helps overcome the relative paucity of training data, and the tendency of the typical MLE-based approach to generate overly terse answers. Critically, the GAN is tightly integrated into the attention mechanism that generates human-interpretable reasons for each answer. This means that the discriminative model of the GAN has the task of assessing whether a candidate answer is generated by a human or not, given the provided reason. This is significant because it drives the generative model to produce high quality answers that are well supported by the associated reasoning. The method also generates the state-of-the-art results on the primary benchmark.
Rights: © 2018 IEEE
RMID: 0030108892
DOI: 10.1109/CVPR.2018.00639
Grant ID: http://purl.org/au-research/grants/arc/CE140100016
http://purl.org/au-research/grants/arc/FL130100102
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.