{"url":"/sota/visual-dialog-on-image-chat","task":{"name":"Visual Dialog","url":"/task/visual-dialogue","note":null},"dataset":{"name":"Image-Chat","url":"/dataset/image-chat"},"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":["BLEU-4","F1","ROUGE-L"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"BLEU-4":"higher","F1":"higher","ROUGE-L":"higher"}},"counts":{"rows":1,"rows_with_code":0,"rows_with_paper_page":1,"rows_dated":1,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Multi-Modal BlenderBot","metrics":{"BLEU-4":"40","F1":"13.1","ROUGE-L":"18"},"uses_additional_data":false,"paper_date":"2020-10-02","paper":"/paper/multi-modal-open-domain-dialogue","paper_url":"https://arxiv.org/abs/2010.01082v1","paper_title":"Multi-Modal Open-Domain Dialogue","code":null,"n_code_links":0,"syntology":null}],"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":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"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"}}}