{"url":"/dataset/epic-sounds","name":"EPIC-SOUNDS","full_name":null,"description_markdown":"**EPIC-SOUNDS** is a large scale dataset of audio annotations capturing temporal extents and class labels within the audio stream of the egocentric videos from EPIC-KITCHENS-100. EPIC-SOUNDS includes 78.4k categorised and 39.2k non-categorised segments of audible events and actions, distributed across 44 classes.\r\n\r\nSource: [Epic-Sounds: A Large-scale Dataset of Actions That Sound](https://arxiv.org/pdf/2302.00646v1.pdf)","description_withheld":null,"homepage":"https://epic-kitchens.github.io/epic-sounds/","introduced_date":"2023-02-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/epic-sounds-a-large-scale-dataset-of-actions","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","first_author":"Jaesung Huh","url":null},"license":{"name":"Creative Commons Attribution-NonCommercial 4.0 International","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Audio Classification","url":"/task/audio-classification","datasets_with_task":"/datasets/task/audio-classification"},{"name":"Human Interaction Recognition","url":"/task/human-interaction-recognition","datasets_with_task":"/datasets/task/human-interaction-recognition"}],"languages":[],"variants":["EPIC-SOUNDS"],"data_loaders":[],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/audio-classification-on-epic-sounds","task":"Audio Classification","dataset_variant":"EPIC-SOUNDS","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Mirasol3B","paper":"/paper/mirasol3b-a-multimodal-autoregressive-model","metrics":{"Accuracy":"78.2"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/human-interaction-recognition-on-epic-sounds","task":"Human Interaction Recognition","dataset_variant":"EPIC-SOUNDS","rows":1,"metrics":["Top-1 accuracy %"],"first_row_in_archive_order":{"model":"Slow-Fast(Finetune by Fivewin team)","paper":"/paper/slow-fast-auditory-streams-for-audio","metrics":{"Top-1 accuracy %":"55.11"},"code_links":[{"title":"ekazakos/auditory-slow-fast","url":"https://github.com/ekazakos/auditory-slow-fast"},{"title":"porcelluscavia/audio-model","url":"https://github.com/porcelluscavia/audio-model"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/ca-2st-cross-attention-in-audio-space-and","title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","date":"2025-03-30","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mirasol3b-a-multimodal-autoregressive-model","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","date":"2023-11-09","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/slow-fast-auditory-streams-for-audio","title":"Slow-Fast Auditory Streams For Audio Recognition","date":"2021-03-05","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}