{"url":"/task/zero-shot-environment-sound-classification","name":"Zero-Shot Environment Sound Classification","slug":"zero-shot-environment-sound-classification","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":6,"papers_with_code":5,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":[],"datasets":[{"url":"/dataset/esc-50","name":"ESC-50","full_name":"ESC-50","num_papers_in_archive":387}],"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":5,"of":5,"tagged_in_all":6,"items":[{"url":"/paper/languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","repositories_listed":6,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/audioclip-extending-clip-to-image-text-and","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","date":"2021-06-24","arxiv_id":"2106.13043","repositories_listed":4,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/imagebind-one-embedding-space-to-bind-them","title":"ImageBind: One Embedding Space To Bind Them All","date":"2023-05-09","arxiv_id":"2305.05665","repositories_listed":3,"syntology":{"n":34,"n_ran":24,"n_unverified":10,"n_pointer_only":32}},{"url":"/paper/wavcaps-a-chatgpt-assisted-weakly-labelled","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","date":"2023-03-30","arxiv_id":"2303.17395","repositories_listed":3,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}}],"syntology_records":5,"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"}}