{"url":"/dataset/epic-hotspot","name":"EPIC-Hotspot","full_name":null,"description_markdown":"From Grounded Human-Object Interaction Hotspots from Video (ICCV'19): We collect annotations for interaction keypoints on EPIC Kitchens in order to quantitatively evaluate our method in parallel to the OPRA dataset (where annotations are available). We note that these annotations are collected purely for evaluation, and are not used for training our model. We select the 20 most frequent verbs, and select 31 nouns that afford these interactions.","description_withheld":null,"homepage":"https://vision.cs.utexas.edu/projects/interaction-hotspots/","introduced_date":"2018-12-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/grounded-human-object-interaction-hotspots","title":"Grounded Human-Object Interaction Hotspots from Video","first_author":"Tushar Nagarajan","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Video-to-image Affordance Grounding","url":"/task/video-to-image-affordance-grounding","datasets_with_task":"/datasets/task/video-to-image-affordance-grounding"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["EPIC-Hotspot"],"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/video-to-image-affordance-grounding-on-epic","task":"Video-to-image Affordance Grounding","dataset_variant":"EPIC-Hotspot","rows":3,"metrics":["KLD","SIM","AUC-J"],"first_row_in_archive_order":{"model":"Afformer","paper":"/paper/affordance-grounding-from-demonstration-video-1","metrics":{"AUC-J":"0.88","KLD":"0.97","SIM":"0.56"},"code_links":[{"title":"showlab/afformer","url":"https://github.com/showlab/afformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/affordance-grounding-from-demonstration-video-1","title":"Affordance Grounding from Demonstration Video to Target Image","date":"2023-03-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-visual-affordance-grounding-from","title":"Learning Visual Affordance Grounding from Demonstration Videos","date":"2021-08-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/grounded-human-object-interaction-hotspots","title":"Grounded Human-Object Interaction Hotspots from Video","date":"2018-12-11","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"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."}