{"url":"/dataset/moma-lrg","name":"MOMA-LRG","full_name":"Multi-Object Multi-Actor activity parsing with Language-Refined Graphs","description_markdown":"A dataset dedicated to multi-object, multi-actor activity parsing.\r\n\r\nThe dataset contains\r\n* Video-level labels (activities)\r\n* Segment-level labels (sub-activities)\r\n* Atomic actions (spatio-temporal scene graph)\r\n\r\nThe scene graph annotations contain object/actor classes and bounding boxes, relationship annotations, and object/actor attributes.","description_withheld":null,"homepage":"https://moma.stanford.edu","introduced_date":"2022-11-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/moma-lrg-language-refined-graphs-for-multi","title":"MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing","first_author":"Zelun Luo","url":null},"license":{"name":"CC BY-SA 4.0","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Video Classification","url":"/task/video-classification","datasets_with_task":"/datasets/task/video-classification"},{"name":"Video Segmentation","url":"/task/video-segmentation","datasets_with_task":"/datasets/task/video-segmentation"},{"name":"Few Shot Action Recognition","url":"/task/few-shot-action-recognition","datasets_with_task":"/datasets/task/few-shot-action-recognition"},{"name":"Scene Graph Detection","url":"/task/scene-graph-detection","datasets_with_task":"/datasets/task/scene-graph-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MOMA-LRG"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/few-shot-action-recognition-on-moma-lrg","task":"Few Shot Action Recognition","dataset_variant":"MOMA-LRG","rows":4,"metrics":["Activity Classification Accuracy (5-shot 5-way)","Subactivity Classification Accuracy (5-shot 5-way)"],"first_row_in_archive_order":{"model":"Name Tuning","paper":"/paper/few-shot-classification-of-interactive","metrics":{"Activity Classification Accuracy (5-shot 5-way)":"97.9","Subactivity Classification Accuracy (5-shot 5-way)":"78.2"},"code_links":[{"title":"zanedurante/vlm_benchmark","url":"https://github.com/zanedurante/vlm_benchmark"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/few-shot-classification-of-interactive","title":"Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)","date":"2024-06-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/moma-lrg-language-refined-graphs-for-multi","title":"MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing","date":"2022-11-28","rows_on_this_dataset":3,"code_links":1,"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."}