Papers › Iterative Context-Aware Graph Inference for Visual Dialog

Iterative Context-Aware Graph Inference for Visual Dialog

5 Apr 2020CVPR 2020 6arXiv:2004.02194archive 2025-07-28

Dan Guo, Hui Wang, Hanwang Zhang, Zheng-Jun Zha, Meng Wang

Visual dialog is a challenging task that requires the comprehension of the semantic dependencies among implicit visual and textual contexts. This task can refer to the relation inference in a graphical model with sparse contexts and unknown graph structure (relation descriptor), and how to model the underlying context-aware relation inference is critical. To this end, we propose a novel Context-Aware Graph (CAG) neural network. Each node in the graph corresponds to a joint semantic feature, including both object-based (visual) and history-related (textual) context representations. The graph structure (relations in dialog) is iteratively updated using an adaptive top-K message passing mechanism. Specifically, in every message passing step, each node selects the most K relevant nodes, and only receives messages from them. Then, after the update, we impose graph attention on all the nodes to get the final graph embedding and infer the answer. In CAG, each node has dynamic relations in the graph (different related K neighbor nodes), and only the most relevant nodes are attributive to the context-aware relational graph inference. Experimental results on VisDial v0.9 and v1.0 datasets show that CAG outperforms comparative methods. Visualization results further validate the interpretability of our method.

PaperPDFConference PDFCode

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

Code

wh0330/CAG_VisDial mentioned on GitHubpytorch 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 AttentionGraph EmbeddingVisual Dialog

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Dialog VisDial v0.9 val CAG MRR 0.6756 #12 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val CAG Mean Rank 3.75 #12 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val CAG R@1 54.64 #12 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val CAG R@10 91.48 #12 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val CAG R@5 83.72 #12 of 18 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std CAG MRR (x 100) 63.49 #60 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std CAG Mean 4.11 #60 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std CAG NDCG (x 100) 56.64 #60 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std CAG R@1 49.85 #60 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std CAG R@10 90.15 #60 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std CAG R@5 80.63 #60 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

Interpretability

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