{"url":"/task/scene-aware-dialogue","name":"Scene-Aware Dialogue","slug":"scene-aware-dialogue","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":8,"papers_with_code":4,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/scene-aware-dialogue-on-avsd","slug":"scene-aware-dialogue-on-avsd","dataset":"AVSD","dataset_url":"/dataset/avsd","rows_in_archive":1,"metrics":["CIDEr"],"first_row_in_archive_order":{"model":"simple","paper_title":"A Simple Baseline for Audio-Visual Scene-Aware Dialog","paper_url":"/paper/a-simple-baseline-for-audio-visual-scene-1","paper_date":"2019-06-01","arxiv_id":null,"code_links":[{"title":"idansc/simple-avsd","url":"https://github.com/idansc/simple-avsd"}],"syntology":null}}],"datasets":[{"url":"/dataset/avsd","name":"AVSD","full_name":"Audio-Visual Scene-Aware Dialog","num_papers_in_archive":14}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":4,"of":4,"tagged_in_all":8,"items":[{"url":"/paper/audio-visual-scene-aware-dialog","title":"Audio-Visual Scene-Aware Dialog","date":"2019-01-25","arxiv_id":"1901.09107","repositories_listed":2,"syntology":null},{"url":"/paper/an-embodied-generalist-agent-in-3d-world","title":"An Embodied Generalist Agent in 3D World","date":"2023-11-18","arxiv_id":"2311.12871","repositories_listed":1,"syntology":{"n":13,"n_ran":3,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/maintaining-common-ground-in-dynamic","title":"Maintaining Common Ground in Dynamic Environments","date":"2021-05-29","arxiv_id":"2105.14207","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/a-simple-baseline-for-audio-visual-scene-1","title":"A Simple Baseline for Audio-Visual Scene-Aware Dialog","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}