Papers › Reasoning Visual Dialogs with Structural and Partial Observations

Reasoning Visual Dialogs with Structural and Partial Observations

11 Apr 2019CVPR 2019 6arXiv:1904.05548archive 2025-07-28

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

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

zilongzheng/visdial-gnn officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph Neural NetworkVisual Dialog

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Dialog VisDial v0.9 val GNN MRR 0.6285 #14 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val GNN Mean Rank 4.57 #14 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val GNN R@1 48.95 #14 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val GNN R@10 88.36 #14 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val GNN R@5 79.65 #14 of 18 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std GNN MRR (x 100) 61.37 #70 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std GNN Mean 4.57 #70 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std GNN NDCG (x 100) 52.82 #70 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std GNN R@1 47.33 #70 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std GNN R@10 87.83 #70 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std GNN R@5 77.98 #70 of 80 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Graph Neural Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections