{"url":"/dataset/paco","name":"PACO","full_name":"Parts and Attributes of Common Objects","description_markdown":"**Parts and Attributes of Common Objects (PACO)** is a detection dataset that goes beyond traditional object boxes and masks and provides richer annotations such as part masks and attributes. It spans 75 object categories, 456 object-part categories and 55 attributes across image (LVIS) and video (Ego4D) datasets. The dataset contains 641K part masks annotated across 260K object boxes, with half of them exhaustively annotated with attributes as well.\r\n\r\nSource: [PACO: Parts and Attributes of Common Objects](https://arxiv.org/pdf/2301.01795v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2301.01795v1.pdf](https://arxiv.org/pdf/2301.01795v1.pdf)","description_withheld":null,"homepage":"https://github.com/facebookresearch/paco","introduced_date":"2023-01-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/paco-parts-and-attributes-of-common-objects","title":"PACO: Parts and Attributes of Common Objects","first_author":"Vignesh Ramanathan","url":null},"license":{"name":"MIT License","url":"https://github.com/facebookresearch/paco/blob/main/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"2D Object Detection","url":"/task/2d-object-detection","datasets_with_task":"/datasets/task/2d-object-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PACO"],"data_loaders":[],"num_papers_in_archive":32,"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."}