Papers › Recursive Visual Attention in Visual Dialog

Recursive Visual Attention in Visual Dialog

6 Dec 2018CVPR 2019 6arXiv:1812.02664archive 2025-07-28

Yulei Niu, Hanwang Zhang, Manli Zhang, Jianhong Zhang, Zhiwu Lu, Ji-Rong Wen

Visual dialog is a challenging vision-language task, which requires the agent to answer multi-round questions about an image. It typically needs to address two major problems: (1) How to answer visually-grounded questions, which is the core challenge in visual question answering (VQA); (2) How to infer the co-reference between questions and the dialog history. An example of visual co-reference is: pronouns (\eg, ``they'') in the question (\eg, ``Are they on or off?'') are linked with nouns (\eg, ``lamps'') appearing in the dialog history (\eg, ``How many lamps are there?'') and the object grounded in the image. In this work, to resolve the visual co-reference for visual dialog, we propose a novel attention mechanism called Recursive Visual Attention (RvA). Specifically, our dialog agent browses the dialog history until the agent has sufficient confidence in the visual co-reference resolution, and refines the visual attention recursively. The quantitative and qualitative experimental results on the large-scale VisDial v0.9 and v1.0 datasets demonstrate that the proposed RvA not only outperforms the state-of-the-art methods, but also achieves reasonable recursion and interpretable attention maps without additional annotations. The code is available at \url{https://github.com/yuleiniu/rva}.

PaperPDFConference PDFCode

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

Code

yuleiniu/rva officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

Question AnsweringVisual DialogVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Dialog VisDial v0.9 val RVA MRR 0.6634 #13 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val RVA Mean Rank 3.93 #13 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val RVA R@1 52.71 #13 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val RVA R@10 90.73 #13 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val RVA R@5 82.97 #13 of 18 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std RVA MRR (x 100) 63.03 #65 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std RVA Mean 4.18 #65 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std RVA NDCG (x 100) 55.59 #65 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std RVA R@1 49.03 #65 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std RVA R@10 89.83 #65 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std RVA R@5 80.40 #65 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.

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