{"url":"/task/video-to-image-affordance-grounding","name":"Video-to-image Affordance Grounding","slug":"video-to-image-affordance-grounding","description_markdown":"Given a demonstration video V and a target image I, the goal of video-to-image affordance grounding predict an affordance heatmap over the target image according to the hand-interacted region in the video, accompanied by the affordance action (e.g., press, turn).","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":4,"papers_with_code":2,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/video-to-image-affordance-grounding-on-opra-1","slug":"video-to-image-affordance-grounding-on-opra-1","dataset":"OPRA (28x28)","dataset_url":"/dataset/opra","rows_in_archive":4,"metrics":["KLD","SIM","AUC-J"],"first_row_in_archive_order":{"model":"Afformer","paper_title":"Affordance Grounding from Demonstration Video to Target Image","paper_url":"/paper/affordance-grounding-from-demonstration-video-1","paper_date":"2023-03-26","arxiv_id":"2303.14644","code_links":[{"title":"showlab/afformer","url":"https://github.com/showlab/afformer"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/video-to-image-affordance-grounding-on-epic","slug":"video-to-image-affordance-grounding-on-epic","dataset":"EPIC-Hotspot","dataset_url":"/dataset/epic-hotspot","rows_in_archive":3,"metrics":["KLD","SIM","AUC-J"],"first_row_in_archive_order":{"model":"Afformer","paper_title":"Affordance Grounding from Demonstration Video to Target Image","paper_url":"/paper/affordance-grounding-from-demonstration-video-1","paper_date":"2023-03-26","arxiv_id":"2303.14644","code_links":[{"title":"showlab/afformer","url":"https://github.com/showlab/afformer"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/video-to-image-affordance-grounding-on-opra","slug":"video-to-image-affordance-grounding-on-opra","dataset":"OPRA","dataset_url":"/dataset/opra","rows_in_archive":3,"metrics":["KLD","Top-1 Action Accuracy"],"first_row_in_archive_order":{"model":"Afformer (ViTDet-B encoder)","paper_title":"Affordance Grounding from Demonstration Video to Target Image","paper_url":"/paper/affordance-grounding-from-demonstration-video-1","paper_date":"2023-03-26","arxiv_id":"2303.14644","code_links":[{"title":"showlab/afformer","url":"https://github.com/showlab/afformer"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}}],"datasets":[{"url":"/dataset/opra","name":"OPRA","full_name":"Online Product Reviews for Affordances","num_papers_in_archive":8},{"url":"/dataset/epic-hotspot","name":"EPIC-Hotspot","full_name":"","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":2,"of":2,"tagged_in_all":4,"items":[{"url":"/paper/affordance-grounding-from-demonstration-video-1","title":"Affordance Grounding from Demonstration Video to Target Image","date":"2023-03-26","arxiv_id":"2303.14644","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/grounded-human-object-interaction-hotspots","title":"Grounded Human-Object Interaction Hotspots from Video","date":"2018-12-11","arxiv_id":"1812.04558","repositories_listed":1,"syntology":null}],"syntology_records":1,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}