FLIPDIAL: A generative model for two-way visual dialogue
We present FLIPDIAL, a generative model for Visual Dialogue that simultaneously plays the role of both participants in a visually-grounded dialogue. Given context in the form of an image and an associated caption summarising the contents of the image, FLIPDIAL learns both to answer questions and put...
Những tác giả chính: | Massiceti, D, Narayanaswamy, S, Torr, P, Dokania, P |
---|---|
Định dạng: | Conference item |
Được phát hành: |
Institute of Electrical and Electronics Engineers
2018
|
Những quyển sách tương tự
-
Visual dialogue without vision or dialogue
Bằng: Massiceti, D, et al.
Được phát hành: (2018) -
Bottom-up top-down cues for weakly-supervised semantic segmentation
Bằng: Hou, Q, et al.
Được phát hành: (2018) -
Multi-agent diverse generative adversarial networks
Bằng: Ghosh, A, et al.
Được phát hành: (2018) -
Random forests versus neural networks - What's best for camera localization?
Bằng: Massiceti, D, et al.
Được phát hành: (2017) -
A semi-supervised deep generative model for human body analysis
Bằng: De Bem, R, et al.
Được phát hành: (2019)