Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Reasoning Visual Dialogs with Structural and Partial Observations

About

We propose a novel model to address the task of Visual Dialog which exhibits complex dialog structures. To obtain a reasonable answer based on the current question and the dialog history, the underlying semantic dependencies between dialog entities are essential. In this paper, we explicitly formalize this task as inference in a graphical model with partially observed nodes and unknown graph structures (relations in dialog). The given dialog entities are viewed as the observed nodes. The answer to a given question is represented by a node with missing value. We first introduce an Expectation Maximization algorithm to infer both the underlying dialog structures and the missing node values (desired answers). Based on this, we proceed to propose a differentiable graph neural network (GNN) solution that approximates this process. Experiment results on the VisDial and VisDial-Q datasets show that our model outperforms comparative methods. It is also observed that our method can infer the underlying dialog structure for better dialog reasoning.

Zilong Zheng, Wenguan Wang, Siyuan Qi, Song-Chun Zhu• 2019

Related benchmarks

TaskDatasetResultRank
Visual DialogVisDial v0.9 (val)
MRR62.85
141
Visual DialogVisDial v1.0 (test-std)
NDCG52.82
77
Visual DialogVisDial v0.9 (test)
MRR41.26
58
Visual Dialog RetrievalVisDial v1.0 (test-standard)
MRR61.37
51
Visual DialogueVisDial v1.0 (test)
NDCG52.82
26
Showing 5 of 5 rows

Other info

Code

Follow for update