{"url":"/dataset/activitynet-entities-1","name":"ActivityNet Entities","full_name":null,"description_markdown":"ActivityNet-Entities, augments the challenging ActivityNet Captions dataset with 158k bounding box annotations, each grounding a noun phrase. This allows training video description models with this data, and importantly, evaluate how grounded or \"true\" such model are to the video they describe.\n\nSource: [https://github.com/facebookresearch/ActivityNet-Entities](https://github.com/facebookresearch/ActivityNet-Entities)\nImage Source: [https://github.com/facebookresearch/ActivityNet-Entities](https://github.com/facebookresearch/ActivityNet-Entities)","description_withheld":null,"homepage":"https://github.com/facebookresearch/ActivityNet-Entities","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/grounded-video-description","title":"Grounded Video Description","first_author":"Luowei Zhou","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":"Video Description","url":"/task/video-description","datasets_with_task":"/datasets/task/video-description"}],"languages":[],"variants":["ActivityNet Entities"],"data_loaders":[{"repo":"https://github.com/facebookresearch/ActivityNet-Entities","url":"https://github.com/facebookresearch/ActivityNet-Entities","frameworks":["pytorch"]}],"num_papers_in_archive":18,"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."}