Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Goal-oriented visual question generation via intermediate rewards
Author: Zhang, J.
Wu, Q.
Shen, C.
Zhang, J.
Lu, J.
van den Hengel, A.
Citation: Lecture Notes in Artificial Intelligence, 2018 / Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (ed./s), vol.Lecture Notes in Computer Science; vol. 11209, pp.189-204
Publisher: Springer
Issue Date: 2018
Series/Report no.: Lecture Notes in Computer Science
ISBN: 9783030012274
ISSN: 0302-9743
Conference Name: 15th European Conference on Computer Vision (ECCV 2018) (8 Sep 2018 - 14 Sep 2018 : Munich)
Editor: Ferrari, V.
Hebert, M.
Sminchisescu, C.
Weiss, Y.
Statement of
Junjie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu and Anton van den Hengel
Abstract: Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge. Towards this end, we propose a Deep Reinforcement Learning framework based on three new intermediate rewards, namely goal-achieved, progressive and informativeness that encourage the generation of succinct questions, which in turn uncover valuable information towards the overall goal. By directly optimizing for questions that work quickly towards fulfilling the overall goal, we avoid the tendency of existing methods to generate long series of inane queries that add little value. We evaluate our model on the GuessWhat?! dataset and show that the resulting questions can help a standard ‘Guesser’ identify a specific object in an image at a much higher success rate.
Keywords: Goal-oriented
intermediate rewards
Rights: © Springer Nature Switzerland AG 2018
DOI: 10.1007/978-3-030-01228-1_12
Appears in Collections:Aurora harvest 8
Australian Institute for Machine Learning publications
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.