{"url":"/sota/visual-dialog-on-visdial-v09-val","task":{"name":"Visual Dialog","url":"/task/visual-dialogue","note":null},"dataset":{"name":"VisDial v0.9 val","url":"/dataset/visdial"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"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.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["MRR","R@1","R@10","R@5","Mean Rank"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"MRR":"higher","R@1":null,"R@10":null,"R@5":null,"Mean Rank":null}},"counts":{"rows":18,"rows_with_code":14,"rows_with_paper_page":18,"rows_dated":18,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"9xFGA (VGG)","metrics":{"MRR":"68.92","Mean Rank":"3.39","R@1":"55.16","R@10":"92.95","R@5":"86.26"},"uses_additional_data":false,"paper_date":"2019-04-11","paper":"/paper/factor-graph-attention","paper_url":"https://arxiv.org/abs/1904.05880v3","paper_title":"Factor Graph Attention","code":"https://github.com/idansc/fga","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DAN","metrics":{"MRR":"66.38","Mean Rank":"4.04","R@1":"53.33","R@10":"90.38","R@5":"82.42"},"uses_additional_data":false,"paper_date":"2019-02-25","paper":"/paper/dual-attention-networks-for-visual-reference","paper_url":"https://arxiv.org/abs/1902.09368v3","paper_title":"Dual Attention Networks for Visual Reference Resolution in Visual Dialog","code":"https://github.com/gicheonkang/DAN-VisDial","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"CorefNMN (ResNet-152)","metrics":{"MRR":"64.1","Mean Rank":"4.45","R@1":"50.92","R@10":"88.81","R@5":"80.18"},"uses_additional_data":false,"paper_date":"2018-09-06","paper":"/paper/visual-coreference-resolution-in-visual","paper_url":"http://arxiv.org/abs/1809.01816v1","paper_title":"Visual Coreference Resolution in Visual Dialog using Neural Module Networks","code":"https://github.com/facebookresearch/corefnmn","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CoAtt","metrics":{"MRR":"63.98","Mean Rank":"4.47","R@1":"50.29","R@10":"88.81","R@5":"80.71"},"uses_additional_data":false,"paper_date":"2017-11-21","paper":"/paper/are-you-talking-to-me-reasoned-visual-dialog","paper_url":"http://arxiv.org/abs/1711.07613v1","paper_title":"Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"CorefNMN","metrics":{"MRR":"63.6","Mean Rank":"4.53","R@1":"50.24","R@10":"88.51","R@5":"79.81"},"uses_additional_data":false,"paper_date":"2018-09-06","paper":"/paper/visual-coreference-resolution-in-visual","paper_url":"http://arxiv.org/abs/1809.01816v1","paper_title":"Visual Coreference Resolution in Visual Dialog using Neural Module Networks","code":"https://github.com/facebookresearch/corefnmn","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DualVD","metrics":{"MRR":"62.94","Mean Rank":"4.17","R@1":"48.64","R@10":"89.94","R@5":"80.89"},"uses_additional_data":false,"paper_date":"2019-11-17","paper":"/paper/dualvd-an-adaptive-dual-encoding-model-for","paper_url":"https://arxiv.org/abs/1911.07251v1","paper_title":"DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue","code":"https://github.com/JXZe/DualVD","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"SF-QIH-se-2","metrics":{"MRR":"62.42","Mean Rank":"4.70","R@1":"48.55","R@10":"87.75","R@5":"78.96"},"uses_additional_data":false,"paper_date":"2018-03-29","paper":"/paper/two-can-play-this-game-visual-dialog-with","paper_url":"http://arxiv.org/abs/1803.11186v1","paper_title":"Two can play this Game: Visual Dialog with Discriminative Question Generation and Answering","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"HCIAE-NP-ATT","metrics":{"MRR":"62.22","Mean Rank":"4.81","R@1":"48.48","R@10":"87.59","R@5":"78.75"},"uses_additional_data":false,"paper_date":"2017-06-05","paper":"/paper/best-of-both-worlds-transferring-knowledge","paper_url":"http://arxiv.org/abs/1706.01554v2","paper_title":"Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model","code":"https://github.com/jiasenlu/visDial.pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"HieCoAtt-QI","metrics":{"MRR":"57.88","Mean Rank":"5.84","R@1":"43.51","R@10":"83.96","R@5":"74.49"},"uses_additional_data":false,"paper_date":"2016-05-31","paper":"/paper/hierarchical-question-image-co-attention-for","paper_url":"http://arxiv.org/abs/1606.00061v5","paper_title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","code":"https://github.com/jiasenlu/HieCoAttenVQA","n_code_links":9,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":10,"model":"HACAN","metrics":{"MRR":"0.6792","Mean Rank":"3.97","R@1":"54.76","R@10":"90.68","R@5":"83.03"},"uses_additional_data":false,"paper_date":"2019-02-25","paper":"/paper/making-history-matter-gold-critic-sequence","paper_url":"http://arxiv.org/abs/1902.09326v3","paper_title":"Making History Matter: History-Advantage Sequence Training for Visual Dialog","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"MVAN","metrics":{"MRR":"0.6765","Mean Rank":"3.73","R@1":"54.65","R@10":"91.47","R@5":"83.85"},"uses_additional_data":false,"paper_date":"2020-04-29","paper":"/paper/multi-view-attention-networks-for-visual","paper_url":"https://arxiv.org/abs/2004.14025v3","paper_title":"Multi-View Attention Network for Visual Dialog","code":"https://github.com/taesunwhang/MVAN-VisDial","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"CAG","metrics":{"MRR":"0.6756","Mean Rank":"3.75","R@1":"54.64","R@10":"91.48","R@5":"83.72"},"uses_additional_data":false,"paper_date":"2020-04-05","paper":"/paper/iterative-context-aware-graph-inference-for","paper_url":"https://arxiv.org/abs/2004.02194v1","paper_title":"Iterative Context-Aware Graph Inference for Visual Dialog","code":"https://github.com/wh0330/CAG_VisDial","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"RVA","metrics":{"MRR":"0.6634","Mean Rank":"3.93","R@1":"52.71","R@10":"90.73","R@5":"82.97"},"uses_additional_data":false,"paper_date":"2018-12-06","paper":"/paper/recursive-visual-attention-in-visual-dialog","paper_url":"http://arxiv.org/abs/1812.02664v2","paper_title":"Recursive Visual Attention in Visual Dialog","code":"https://github.com/yuleiniu/rva","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"GNN","metrics":{"MRR":"0.6285","Mean Rank":"4.57","R@1":"48.95","R@10":"88.36","R@5":"79.65"},"uses_additional_data":false,"paper_date":"2019-04-11","paper":"/paper/reasoning-visual-dialogs-with-structural-and","paper_url":"https://arxiv.org/abs/1904.05548v2","paper_title":"Reasoning Visual Dialogs with Structural and Partial Observations","code":"https://github.com/zilongzheng/visdial-gnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"MN-QIH-D","metrics":{"MRR":"0.5965","Mean Rank":"5.46","R@1":"45.55","R@10":"85.37","R@5":"76.22"},"uses_additional_data":false,"paper_date":"2016-11-26","paper":"/paper/visual-dialog","paper_url":"http://arxiv.org/abs/1611.08669v5","paper_title":"Visual Dialog","code":"https://github.com/facebookresearch/ParlAI","n_code_links":11,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"HRE-QIH-D","metrics":{"MRR":"0.5846","Mean Rank":"5.72","R@1":"44.67","R@10":"84.22","R@5":"74.50"},"uses_additional_data":false,"paper_date":"2016-11-26","paper":"/paper/visual-dialog","paper_url":"http://arxiv.org/abs/1611.08669v5","paper_title":"Visual Dialog","code":"https://github.com/facebookresearch/ParlAI","n_code_links":11,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"HRE-QIH-D","metrics":{"MRR":"0.5807","Mean Rank":"5.78","R@1":"43.82","R@10":"84.07","R@5":"74.68"},"uses_additional_data":false,"paper_date":"2016-11-26","paper":"/paper/visual-dialog","paper_url":"http://arxiv.org/abs/1611.08669v5","paper_title":"Visual Dialog","code":"https://github.com/facebookresearch/ParlAI","n_code_links":11,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"AMEM","metrics":{"Mean Rank":"4.86","R@1":"48.53","R@10":"87.43","R@5":"78.66"},"uses_additional_data":false,"paper_date":"2017-09-23","paper":"/paper/visual-reference-resolution-using-attention","paper_url":"http://arxiv.org/abs/1709.07992v3","paper_title":"Visual Reference Resolution using Attention Memory for Visual Dialog","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":5,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":4,"n_unverified":12,"n_samples":16,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":8,"n_unverified":12,"n_samples":20,"n_pointer_only_licence":1,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}