Browse › Computer Vision › Visual Dialog › Visual Dialog v1.0 test-std

Visual Dialog archive 2025-07-28

Visual Dialog v1.0 test-std Benchmark (Visual Dialog)

80 rows 14 with code listed 6 metrics Dataset page

Syntology Since the archive (Syntology): none placed; no newer paper judged to report on this board so far.

Visual Dialog requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Specifically, given an image, a dialog history, and a follow-up question about the image, the task is to answer the question.

The archive carries no text for this table; the description above is the archive's text for the task Visual Dialog. archive 2025-07-28

Over time archive 2025-07-28

Direction inferred from the metric name, not from the archive: NDCG (x 100) (higher is better), MRR (x 100) (higher is better). Not inferred (points only, no best-so-far line): R@1, R@5, R@10, Mean. Points are placed at the row's paper date, not an evaluation date; 16 of 80 rows carry one.

The chart needs JavaScript; the table below carries every value.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 Single 78.745.7529.565.782.456.54 – – – not matched report
2 P1P2+Distill+Ensemble 77.9256.244.4568.983.785.41 – – – not matched report
3 Ensemble + Fine-tuning 76.4356.3545.1768.1282.175.79 – – – not matched report
4 ensemble, finetune 76.1756.4244.3270.2384.525.47 – – – not matched report
5 VD-PCR 76.1456.0544.7568.482.755.72 – – – not matched report
6 Ensemble 75.3551.1738.962.8277.986.69 – – – not matched report
7 Ensemble + Finetune 74.8852.1438.9266.680.656.53 – Paper Code 2019 linked, not harvested report
8 bert-double-stream-finetuning 74.6262.6554.3770.7583.335.89 – – – not matched report
9 CE-finetuned, single model 74.4750.7437.9564.1280.06.28 – – – not matched report
10 2 73.3649.2636.3562.4278.127.0 – – – not matched report
11 2 73.1543.0727.8260.3876.557.42 – – – not matched report
12 5_4 73.0848.3734.6562.9877.537.05 – – – not matched report
13 7 73.0756.0344.268.4581.625.98 – – – not matched report
14 1 72.9956.7345.4268.9281.736.0 – – – not matched report
15 5-2 72.8549.0335.8862.8877.757.07 – – – not matched report
16 2 Step: Factor Graph Attention + VD-Bert 72.8369.9258.381.5589.63.84 – Paper Code 2021 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified report
17 1 72.856.6744.8268.6781.95.98 – – – not matched report
18 10 72.5849.4735.7764.1578.256.9 – – – not matched report
19 Disc, Dense, 4 Ensemble. 72.4155.1143.2367.6579.776.55 – – – not matched report
20 shanshandu 72.3557.1945.370.1582.386.04 – – – not matched report
21 1 72.3357.1345.1769.9582.45.85 – – – not matched report
22 20 72.3347.5433.563.2877.337.14 – – – not matched report
23 Two-Step(refactor) 72.1670.4158.1783.8590.833.66 – – – not matched report
24 simple_test 71.9141.6625.8560.1274.678.3 – – – not matched report
25 1 71.8256.3444.2269.6581.76.04 – – – not matched report
26 5TS 70.0839.6125.6553.6270.129.01 – – – not matched report
27 Bert(two-stream) 68.0863.9250.7879.5389.64.28 – – – not matched report
28 Ensemble FGA + BERT 67.0970.9557.0788.4295.082.91 – – – not matched report
29 CARE(Single Model) 64.7964.6251.8280.3589.954.29 – – – not matched report
30 sdfsdaf 64.4858.5744.2776.1586.425.13 – – – not matched report
31 MRR ensemble (Naive) 64.0471.2458.2787.5594.452.96 – – – not matched report
32 CAF 63.9468.1654.6784.9593.13.3 – – – not matched report
33 w/ VQA + CC, single model 63.8767.553.8584.6793.253.32 – – – not matched report
34 test1 63.8767.553.8584.6793.253.32 – – – not matched report
35 sh101 63.7567.4953.7585.0293.253.31 – – – not matched report
36 SCL_48 60.9166.6352.5284.192.273.41 – – – not matched report
37 Transformer+2cons 60.3366.5352.6284.1292.53.4 – – – not matched report
38 single-model 60.3164.9550.4883.1593.153.44 – – – not matched report
39 1 60.1964.2550.8880.9290.64.11 – – – not matched report
40 211 59.6964.1450.6280.7789.834.18 – – – not matched report
41 MVAN 59.3764.8451.4581.1290.653.97 – Paper Code 2020 linked, not harvested report
42 single model 59.3366.251.6285.0593.73.25 – – – not matched report
43 gr 59.2364.5851.2580.9290.054.03 – – – not matched report
44 lkh(single-model) 59.062.6549.4878.188.354.5 – – – not matched report
45 lijunlin_7 58.5963.750.379.4789.154.26 – – – not matched report
46 wqedasd(single model) 58.5661.8748.478.088.64.49 – – – not matched report
47 Bert2constraints 58.5165.751.7382.9791.973.68 – – – not matched report
48 zxcdd 58.4964.3150.880.889.654.11 – – – not matched report
49 jiuyigedian 58.2564.7951.3281.090.383.98 – – – not matched report
50 disc 58.1964.4350.780.8390.184.13 – – – not matched report
51 lijunlin_9 58.1463.3149.6880.4589.254.31 – – – not matched report
52 NMN 58.158.844.1576.8886.884.4 – Paper Code 2017 linked, not harvested report
53 zuizhong 57.8264.350.5881.2590.034.07 – – – not matched report
54 clean_wac_4freeze 57.664.5749.7582.2391.673.67 – – – not matched report
55 DAN 57.5963.249.6379.7589.354.3 – Paper Code 2019 official (archive's flag): 1 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified report
56 mvan_len40_test 57.3947.0336.9356.4765.813.3 – – – not matched report
57 Synergistic 57.3262.2047.9080.434.17 – Paper – 2019 no code linked report
58 5xFGA (F-RCNNx101) 57.2069.355.6586.7394.053.14 – Paper Code 2019 linked, not harvested report
59 HACAN 57.1764.2250.8880.6389.454.20 – Paper – 2019 no code linked report
60 CAG 56.6463.4949.8580.6390.154.11 – Paper Code 2020 linked, not harvested report
61 kbgn_disc_5 56.3862.6848.680.189.484.22 – – – not matched report
62 DualVD 56.3263.2349.2580.2389.74.11 – Paper Code 2019 linked, not harvested report
63 ERIC666 55.9463.349.1881.089.64.2 – – – not matched report
64 eightepoch 55.8862.2447.5880.4589.724.09 – – – not matched report
65 RVA 55.5963.0349.0380.4089.834.18 – Paper Code 2018 linked, not harvested report
66 single-model 55.2162.5647.4581.5592.03.82 – – – not matched report
67 CorefNMN (ResNet-152) 54.7061.5047.5578.1088.804.40 – Paper Code 2018 linked, not harvested report
68 jkl 53.259.9646.3576.7886.485.12 – – – not matched report
69 trainval_ch_9 53.1945.8435.954.9761.720.71 – – – not matched report
70 GNN 52.8261.3747.3377.9887.834.57 – Paper Code 2019 linked, not harvested report
71 DLC-4 52.5761.0946.8378.2287.424.65 – – – not matched report
72 gat_disc_relto_4 51.8755.6942.770.1779.727.87 – – – not matched report
73 adasd 49.9460.1145.677.5387.94.7 – – – not matched report
74 gat_disc_3 47.5153.1941.465.8574.1511.96 – – – not matched report
75 MN-QIH-D 47.555.540.9872.3083.305.92 – Paper Code 2016 community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified report
76 paratraining1epoch 46.7553.336.8373.4583.15.91 – – – not matched report
77 HRE-QIH-D 45.554.239.9370.4581.506.41 – Paper Code 2016 community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified report
78 MN-QIH-D 45.355.440.9572.4582.835.95 – Paper Code 2016 community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified report
79 czczx 23.029.9716.6243.5853.0522.05 – – – not matched report
80 qqhe 11.847.253.027.2212.2249.61 – – – not matched report

All 80 rows shown. 16 link to a paper page on this site; 0 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”: of the code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and U are unverified (harvested, no recorded run). Of the N, C constructed an object rather than computing a result (a part of N, never taken away from it), K ran with no instrument failure (honoured or violated the contract Syntology drafted, or ran with no contract checked) and I are failures of Syntology's instrument, not of the code (a wrong contract draft, or a contract check that could not run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 5 rows have a graph line, from 3 distinct papers. Rows whose paper has a sample that ran: 5 (2 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument). Papers: 3 with a sample that ran: 2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument. Whose code ran. When the archive marks a repository official for the row's paper, the cell starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code): “official (archive's flag): N ran” counts the samples from it that ran, instrument failures included; “official: harvested, nothing ran”; when it has no sample for this paper and other samples ran, “community repositories only” if every one came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, and “official: no sample here; runs from other or unrecorded repositories” if any came from a repository named in the paper or found in its text by Syntology, or has no repository recorded; “official: harvested for another paper” (no sample from it is linked to this paper) or “official: not harvested”. No state is printed when the archive marks none official. The cell's tooltip names the repositories the samples that ran came from. Of the 5 rows with a graph line, 5 have an archive-official repository: on 2 a sample from it ran (2 with a run with no instrument failure), on 3 the samples that ran came from community repositories only, and on 0 from other or unrecorded repositories. The filters above hide rows and never renumber them; the first two count, by default, only a run with no instrument failure, and offer any run, instrument failures included. Counting each paper once, of 11 samples: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. Separately, 3 of those 11 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. Per-sample status is on the paper page; each Ran cell links to that paper's sample list. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Since the archive Syntology

Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 1 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,596 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and none proposed a result, so none await a verdict and none were placed. Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.

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