FlipDial: A Generative Model for Two-Way Visual Dialogue

Abstract

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 forward questions, capable of generating entire sequences of dialogue (question-answer pairs) which are diverse and relevant to the image. To do this, FlipDial relies on a simple but surprisingly powerful idea: it uses convolutional neural networks (CNNs) to encode entire dialogues directly, implicitly capturing dialogue context, and conditional VAEs to learn the generative model. FlipDial outperforms the state-of-the-art model in the sequential answering task (one-way visual dialogue) on the VisDial dataset by 5 points in Mean Rank using the generated answers. We are the first to extend this paradigm to full two-way visual dialogue, where our model is capable of generating both questions and answers in sequence based on a visual input, for which we propose a set of novel evaluation measures and metrics.

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Conditional Image Generation with PixelCNN Decoders
• Pixel Recurrent Neural Networks
• VQA: Visual Question Answering
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• A Convolutional Neural Network for Modelling Sentences
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Deep Visual-Semantic Alignments for Generating Image Descriptions
• Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
• Creativity: Generating Diverse Questions using Variational Autoencoders

Cited by in corpus (8)

• Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog
• Reasoning Visual Dialogs with Structural and Partial Observations
• Visual Dialogue without Vision or Dialogue
• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• Generative Visual Dialogue System via Adaptive Reasoning and Weighted Likelihood Estimation
• OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
• Saying the Unseen: Video Descriptions via Dialog Agents
• Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents