{"url":"/task/sound-prompted-semantic-segmentation","name":"Sound Prompted Semantic Segmentation","slug":"sound-prompted-semantic-segmentation","description_markdown":"Sound prompted semantic segmentation aims to predict a segmentation mask given an audio prompt for the object in question. For example, given the sound of a car, the task is to segment the cars in the image.","categories":[{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Medical","url":"/area/medical"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":4,"papers_with_code":3,"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":1},"benchmarks":[{"leaderboard":"/sota/sound-prompted-semantic-segmentation-on","slug":"sound-prompted-semantic-segmentation-on","dataset":"ADE20K","dataset_url":"/dataset/ade20k","rows_in_archive":4,"metrics":["mAP","mIoU"],"first_row_in_archive_order":{"model":"DenseAV","paper_title":"Separating the \"Chirp\" from the \"Chat\": Self-supervised Visual Grounding of Sound and Language","paper_url":"/paper/separating-the-chirp-from-the-chat-self","paper_date":"2024-06-09","arxiv_id":"2406.05629","code_links":[{"title":"mhamilton723/DenseAV","url":"https://github.com/mhamilton723/DenseAV"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/ade20k","name":"ADE20K","full_name":"","num_papers_in_archive":1213}],"subtasks":[],"parent_tasks":[{"url":"/task/semantic-segmentation","name":"Semantic Segmentation"}],"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":4,"items":[{"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/separating-the-chirp-from-the-chat-self","title":"Separating the \"Chirp\" from the \"Chat\": Self-supervised Visual Grounding of Sound and Language","date":"2024-06-09","arxiv_id":"2406.05629","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/contrastive-audio-visual-masked-autoencoder","title":"Contrastive Audio-Visual Masked Autoencoder","date":"2022-10-02","arxiv_id":"2210.07839","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":3,"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"}}