{"url":"/task/gzsl-video-classification","name":"GZSL Video Classification","slug":"gzsl-video-classification","description_markdown":"Audio-visual zero-shot learning aims to recognize unseen categories based on paired audio-visual sequences.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":7,"papers_with_code":3,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"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":1},"benchmarks":[{"leaderboard":"/sota/gzsl-video-classification-on-activitynet-gzsl-1","slug":"gzsl-video-classification-on-activitynet-gzsl-1","dataset":"ActivityNet-GZSL(main)","dataset_url":"/dataset/activitynet","rows_in_archive":7,"metrics":["HM","ZSL"],"first_row_in_archive_order":{"model":"KDA","paper_title":"Boosting Audio-visual Zero-shot Learning with Large Language Models","paper_url":"/paper/boosting-audio-visual-zero-shot-learning-with","paper_date":"2023-11-21","arxiv_id":"2311.12268","code_links":[{"title":"chenhaoxing/KDA","url":"https://github.com/chenhaoxing/KDA"}],"syntology":null}},{"leaderboard":"/sota/gzsl-video-classification-on-ucf-gzsl-main","slug":"gzsl-video-classification-on-ucf-gzsl-main","dataset":"UCF-GZSL(main)","dataset_url":null,"rows_in_archive":7,"metrics":["HM","ZSL"],"first_row_in_archive_order":{"model":"KDA","paper_title":"Boosting Audio-visual Zero-shot Learning with Large Language Models","paper_url":"/paper/boosting-audio-visual-zero-shot-learning-with","paper_date":"2023-11-21","arxiv_id":"2311.12268","code_links":[{"title":"chenhaoxing/KDA","url":"https://github.com/chenhaoxing/KDA"}],"syntology":null}},{"leaderboard":"/sota/gzsl-video-classification-on-vggsound-gzsl-1","slug":"gzsl-video-classification-on-vggsound-gzsl-1","dataset":"VGGSound-GZSL(main)","dataset_url":null,"rows_in_archive":7,"metrics":["HM","ZSL"],"first_row_in_archive_order":{"model":"KDA","paper_title":"Boosting Audio-visual Zero-shot Learning with Large Language Models","paper_url":"/paper/boosting-audio-visual-zero-shot-learning-with","paper_date":"2023-11-21","arxiv_id":"2311.12268","code_links":[{"title":"chenhaoxing/KDA","url":"https://github.com/chenhaoxing/KDA"}],"syntology":null}},{"leaderboard":"/sota/gzsl-video-classification-on-activitynet-gzsl","slug":"gzsl-video-classification-on-activitynet-gzsl","dataset":"ActivityNet-GZSL (cls)","dataset_url":"/dataset/activitynet","rows_in_archive":4,"metrics":["HM","ZSL"],"first_row_in_archive_order":{"model":"KDA","paper_title":"Boosting Audio-visual Zero-shot Learning with Large Language Models","paper_url":"/paper/boosting-audio-visual-zero-shot-learning-with","paper_date":"2023-11-21","arxiv_id":"2311.12268","code_links":[{"title":"chenhaoxing/KDA","url":"https://github.com/chenhaoxing/KDA"}],"syntology":null}},{"leaderboard":"/sota/gzsl-video-classification-on-ucf-gzsl-cls","slug":"gzsl-video-classification-on-ucf-gzsl-cls","dataset":"UCF-GZSL (cls)","dataset_url":null,"rows_in_archive":4,"metrics":["HM","ZSL"],"first_row_in_archive_order":{"model":"KDA","paper_title":"Boosting Audio-visual Zero-shot Learning with Large Language Models","paper_url":"/paper/boosting-audio-visual-zero-shot-learning-with","paper_date":"2023-11-21","arxiv_id":"2311.12268","code_links":[{"title":"chenhaoxing/KDA","url":"https://github.com/chenhaoxing/KDA"}],"syntology":null}},{"leaderboard":"/sota/gzsl-video-classification-on-vggsound-gzsl","slug":"gzsl-video-classification-on-vggsound-gzsl","dataset":"VGGSound-GZSL (cls)","dataset_url":null,"rows_in_archive":4,"metrics":["HM","ZSL"],"first_row_in_archive_order":{"model":"KDA","paper_title":"Boosting Audio-visual Zero-shot Learning with Large Language Models","paper_url":"/paper/boosting-audio-visual-zero-shot-learning-with","paper_date":"2023-11-21","arxiv_id":"2311.12268","code_links":[{"title":"chenhaoxing/KDA","url":"https://github.com/chenhaoxing/KDA"}],"syntology":null}}],"datasets":[{"url":"/dataset/activitynet","name":"ActivityNet","full_name":"","num_papers_in_archive":807}],"subtasks":[],"parent_tasks":[{"url":"/task/zero-shot-learning","name":"Zero-Shot Learning"}],"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":3,"of":3,"tagged_in_all":7,"items":[{"url":"/paper/temporal-and-cross-modal-attention-for-audio","title":"Temporal and cross-modal attention for audio-visual zero-shot learning","date":"2022-07-20","arxiv_id":"2207.09966","repositories_listed":2,"syntology":null},{"url":"/paper/boosting-audio-visual-zero-shot-learning-with","title":"Boosting Audio-visual Zero-shot Learning with Large Language Models","date":"2023-11-21","arxiv_id":"2311.12268","repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-generalised-zero-shot-learning","title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language","date":"2022-03-07","arxiv_id":"2203.03598","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":1,"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"}}