{"url":"/sota/visual-dialog-on-visdial-v10-test-std","task":{"name":"Visual Dialog","url":"/task/visual-dialogue","note":null},"dataset":{"name":"VisDial v1.0 test-std","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","Mean Rank","NDCG","R@1","R@10","R@5"],"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","Mean Rank":null,"NDCG":"higher","R@1":null,"R@10":null,"R@5":null}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"5xFGA + LS*+","metrics":{"MRR":"0.7124","Mean Rank":"2.96","R@1":"58.28","R@10":"94.45","R@5":"87.55"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/ensemble-of-mrr-and-ndcg-models-for-visual","paper_url":"https://arxiv.org/abs/2104.07511v3","paper_title":"Ensemble of MRR and NDCG models for Visual Dialog","code":"https://github.com/idansc/mrr-ndcg","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":2,"model":"Two-Step","metrics":{"MRR":"0.7041","Mean Rank":"3.66","NDCG":"72.16","R@1":"58.18","R@10":"90.83","R@5":"83.85"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/ensemble-of-mrr-and-ndcg-models-for-visual","paper_url":"https://arxiv.org/abs/2104.07511v3","paper_title":"Ensemble of MRR and NDCG models for Visual Dialog","code":"https://github.com/idansc/mrr-ndcg","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":3,"model":"5xFGA + LS","metrics":{"NDCG":"64.04"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/ensemble-of-mrr-and-ndcg-models-for-visual","paper_url":"https://arxiv.org/abs/2104.07511v3","paper_title":"Ensemble of MRR and NDCG models for Visual Dialog","code":"https://github.com/idansc/mrr-ndcg","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6,"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"}}}