{"url":"/dataset/avmit","name":"AVMIT","full_name":"Audiovisual Moments in Time","description_markdown":"Audiovisual Moments in Time (AVMIT) is a large-scale dataset of audiovisual action events. The dataset includes the annotation of 57,177 audiovisual videos from the Moments in Time dataset, each independently evaluated by 3 of 11 trained participants. Each annotation pertains to whether the labelled audiovisual action event is present and whether it is the most prominent feature of the video. The dataset also provides a curated test set of 960 videos across 16 classes, suitable for comparative experiments involving computational models and human participants, specifically when addressing research questions where audiovisual correspondence is of critical importance.","description_withheld":null,"homepage":"","introduced_date":"2023-08-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/audiovisual-moments-in-time-a-large-scale","title":"Audiovisual Moments in Time: A Large-Scale Annotated Dataset of Audiovisual Actions","first_author":"Michael Joannou","url":null},"license":{"name":"Creative Commons Attribution License","url":"https://zenodo.org/records/8253350"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Semantic correspondence","url":"/task/semantic-correspondence","datasets_with_task":"/datasets/task/semantic-correspondence"},{"name":"audio-visual learning","url":"/task/audio-visual-learning","datasets_with_task":"/datasets/task/audio-visual-learning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["AVMIT"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}