DeepAI AI Chat
Log In Sign Up

Visual Reference Resolution using Attention Memory for Visual Dialog

by   Paul Hongsuck Seo, et al.
Disney Research

Visual dialog is a task of answering a series of inter-dependent questions given an input image, and often requires to resolve visual references among the questions. This problem is different from visual question answering (VQA), which relies on spatial attention (a.k.a. visual grounding) estimated from an image and question pair. We propose a novel attention mechanism that exploits visual attentions in the past to resolve the current reference in the visual dialog scenario. The proposed model is equipped with an associative attention memory storing a sequence of previous (attention, key) pairs. From this memory, the model retrieves the previous attention, taking into account recency, which is most relevant for the current question, in order to resolve potentially ambiguous references. The model then merges the retrieved attention with a tentative one to obtain the final attention for the current question; specifically, we use dynamic parameter prediction to combine the two attentions conditioned on the question. Through extensive experiments on a new synthetic visual dialog dataset, we show that our model significantly outperforms the state-of-the-art (by 16 resolution plays an important role. Moreover, the proposed model achieves superior performance ( 2 despite having significantly fewer parameters than the baselines.


page 8

page 12

page 13

page 14

page 15

page 16


Dual Attention Networks for Visual Reference Resolution in Visual Dialog

Visual dialog (VisDial) is a task which requires an AI agent to answer a...

Unsupervised Visual-Linguistic Reference Resolution in Instructional Videos

We propose an unsupervised method for reference resolution in instructio...

Reasoning Over History: Context Aware Visual Dialog

While neural models have been shown to exhibit strong performance on sin...

ORD: Object Relationship Discovery for Visual Dialogue Generation

With the rapid advancement of image captioning and visual question answe...

Neuro-Symbolic Visual Dialog

We propose Neuro-Symbolic Visual Dialog (NSVD) -the first method to comb...

Factor Graph Attention

Dialog is an effective way to exchange information, but subtle details a...

Referring to the recently seen: reference and perceptual memory in situated dialog

From theoretical linguistic and cognitive perspectives, situated dialog ...