{"url":"/dataset/mmac-captions","name":"MMAC Captions","full_name":null,"description_markdown":"We provide a dataset called MMAC Captions for sensor-augmented egocentric-video captioning. The dataset contains 5,002 activity descriptions by extending the [CMU-MMAC dataset](http://kitchen.cs.cmu.edu/index.php). A number of activity description examples can be found in the homepage.","description_withheld":null,"homepage":"https://github.com/hitachi-rd-cv/mmac_captions","introduced_date":"2021-09-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/sensor-augmented-egocentric-video-captioning","title":"Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention","first_author":"Katsuyuki Nakamura","url":null},"license":{"name":"MIT","url":"https://github.com/hitachi-rd-cv/mmac_captions/blob/main/LICENSE.txt"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Time series","url":"/datasets/modality/time-series"}],"tasks":[{"name":"Video Captioning","url":"/task/video-captioning","datasets_with_task":"/datasets/task/video-captioning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MMAC Captions"],"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."}