Papers › Dual Attention Networks for Visual Reference Resolution in Visual Dialog

Dual Attention Networks for Visual Reference Resolution in Visual Dialog

25 Feb 2019IJCNLP 2019 11arXiv:1902.09368archive 2025-07-28

Gi-Cheon Kang, Jaeseo Lim, Byoung-Tak Zhang

Visual dialog (VisDial) is a task which requires an AI agent to answer a series of questions grounded in an image. Unlike in visual question answering (VQA), the series of questions should be able to capture a temporal context from a dialog history and exploit visually-grounded information. A problem called visual reference resolution involves these challenges, requiring the agent to resolve ambiguous references in a given question and find the references in a given image. In this paper, we propose Dual Attention Networks (DAN) for visual reference resolution. DAN consists of two kinds of attention networks, REFER and FIND. Specifically, REFER module learns latent relationships between a given question and a dialog history by employing a self-attention mechanism. FIND module takes image features and reference-aware representations (i.e., the output of REFER module) as input, and performs visual grounding via bottom-up attention mechanism. We qualitatively and quantitatively evaluate our model on VisDial v1.0 and v0.9 datasets, showing that DAN outperforms the previous state-of-the-art model by a significant margin.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1902.09368")

Code

Syntology Ran 1 of 7 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: official repository: 4 samples from 1 repository, 0 ran; community (archive-listed): 3 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gicheonkang/DAN-VisDial officialmentioned in papermentioned on GitHubpytorchMIT report
phellonchen/DMRM mentioned 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

7 samples harvested; 1 ran; 1 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
6unverified

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

create_glove_embedding_init gicheonkang/DAN-VisDial/utils/utils.py official repository unverified MIT (permissive) · 40ad7ca583756bff · report
get_gt_ranks gicheonkang/DAN-VisDial/utils/eval_utils.py official repository unverified MIT (permissive) · 72d5007cbbf2c295 · report
load_imageid gicheonkang/DAN-VisDial/utils/utils.py official repository unverified MIT (permissive) · e90714af510bbb7f · report
scores_to_ranks gicheonkang/DAN-VisDial/utils/eval_utils.py official repository unverified MIT (permissive) · 26ec77dabb4db96d · report
pil_loader phellonchen/DMRM/utils.py community (archive-listed) ran · honoured contract MIT (permissive) · 1df9a5ffd9b38c34 · report
load_folder phellonchen/DMRM/utils.py community (archive-listed) unverified MIT (permissive) · 8c1252eacab71602 · report
load_imageid phellonchen/DMRM/utils.py community (archive-listed) unverified MIT (permissive) · bf90bd27fe08f3a2 · report

Tasks

AI AgentQuestion AnsweringVisual DialogVisual GroundingVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Dialog VisDial v0.9 val DAN MRR 66.38 #2 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val DAN Mean Rank 4.04 #2 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val DAN R@1 53.33 #2 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val DAN R@10 90.38 #2 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val DAN R@5 82.42 #2 of 18 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std DAN MRR (x 100) 63.2 #55 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std DAN Mean 4.3 #55 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std DAN NDCG (x 100) 57.59 #55 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std DAN R@1 49.63 #55 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std DAN R@10 89.35 #55 of 80 Archive leaderboard report
Visual Dialog Visual Dialog v1.0 test-std DAN R@5 79.75 #55 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