{"url":"/dataset/mmact","name":"MMAct","full_name":null,"description_markdown":"MMAct is a large-scale dataset for multi/cross modal action understanding. This dataset has been recorded from 20 distinct subjects with seven different types of modalities: RGB videos, keypoints, acceleration, gyroscope, orientation, Wi-Fi and pressure signal. The dataset consists of more than 36k video clips for 37 action classes covering a wide range of daily life activities such as desktop-related and check-in-based ones in four different distinct scenarios. \r\n\r\nSource: [MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding](/paper/mmact-a-large-scale-dataset-for-cross-modal)","description_withheld":null,"homepage":"https://mmact19.github.io/2019/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/mmact-a-large-scale-dataset-for-cross-modal","title":"MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding","first_author":"Quan Kong","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Multimodal Activity Recognition","url":"/task/multimodal-activity-recognition","datasets_with_task":"/datasets/task/multimodal-activity-recognition"}],"languages":[],"variants":["MMAct"],"data_loaders":[],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multimodal-activity-recognition-on-mmact","task":"Multimodal Activity Recognition","dataset_variant":"MMAct","rows":3,"metrics":["F1-Score (Cross-Session)","F1-Score (Cross-Subject)"],"first_row_in_archive_order":{"model":"MuMu","paper":"/paper/mumu-cooperative-multitask-learning-based","metrics":{"F1-Score (Cross-Session)":"87.50","F1-Score (Cross-Subject)":"76.28"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mumu-cooperative-multitask-learning-based","title":"MuMu: Cooperative Multitask Learning-based Guided Multimodal Fusion","date":"2022-02-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/fusion-gcn-multimodal-action-recognition","title":"Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks","date":"2021-09-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-gat-a-graphical-attention-based","title":"Multi-GAT: A Graphical Attention-based Hierarchical Multimodal Representation Learning Approach for Human Activity Recognition","date":"2021-04-01","rows_on_this_dataset":1,"code_links":0,"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."}