Visual Question Answering with Question Representation Update (QRU)
Other conference paper


Full Text

Other information
AbstractOur method aims at reasoning over natural language questions and visual images. Given a natural language question about an image, our model updates the question representation iteratively by selecting image regions relevant to the query and learns to give the correct answer. Our model contains several reasoning layers, exploiting complex visual relations in the visual question answering (VQA) task. The proposed network is end-to-end trainable through back-propagation, where its weights are initialized using pre-trained convolutional neural network (CNN) and gated recurrent unit (GRU). Our method is evaluated on challenging datasets of COCO-QA [19] and VQA [2] and yields state-of-the-art performance.
All Author(s) ListRuiyu LI, Jiaya JIA
Name of ConferenceThe 30th Conference on Neural Information Processing Systems (NIPS 2016)
Start Date of Conference04/12/2016
End Date of Conference09/12/2016
Place of ConferenceBarcelona
Country/Region of ConferenceSpain
Year2016
LanguagesEnglish-United States

Last updated on 2018-18-01 at 02:18