Papers › Factor Graph Attention

Factor Graph Attention

11 Apr 2019CVPR 2019 6arXiv:1904.05880archive 2025-07-28

Idan Schwartz, Seunghak Yu, Tamir Hazan, Alexander Schwing

Dialog is an effective way to exchange information, but subtle details and nuances are extremely important. While significant progress has paved a path to address visual dialog with algorithms, details and nuances remain a challenge. Attention mechanisms have demonstrated compelling results to extract details in visual question answering and also provide a convincing framework for visual dialog due to their interpretability and effectiveness. However, the many data utilities that accompany visual dialog challenge existing attention techniques. We address this issue and develop a general attention mechanism for visual dialog which operates on any number of data utilities. To this end, we design a factor graph based attention mechanism which combines any number of utility representations. We illustrate the applicability of the proposed approach on the challenging and recently introduced VisDial datasets, outperforming recent state-of-the-art methods by 1.1% for VisDial0.9 and by 2% for VisDial1.0 on MRR. Our ensemble model improved the MRR score on VisDial1.0 by more than 6%.

PaperPDFConference PDFCode

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

Code

idansc/fga officialmentioned in papermentioned 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 AttentionQuestion AnsweringVisual DialogVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Dialog VisDial v0.9 val 9xFGA (VGG) MRR 68.92 #1 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val 9xFGA (VGG) Mean Rank 3.39 #1 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val 9xFGA (VGG) R@1 55.16 #1 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val 9xFGA (VGG) R@10 92.95 #1 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val 9xFGA (VGG) R@5 86.26 #1 of 18 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std 5xFGA (F-RCNNx101) MRR (x 100) 69.3 #58 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std 5xFGA (F-RCNNx101) Mean 3.14 #58 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std 5xFGA (F-RCNNx101) NDCG (x 100) 57.20 #58 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std 5xFGA (F-RCNNx101) R@1 55.65 #58 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std 5xFGA (F-RCNNx101) R@10 94.05 #58 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std 5xFGA (F-RCNNx101) R@5 86.73 #58 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

Introduced by this paper: FGA

FGAInterpretability

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