{"url":"/task/affordance-detection","name":"Affordance Detection","slug":"affordance-detection","description_markdown":"Affordance detection refers to identifying the potential action possibilities of objects in an image, which is an important ability for robot perception and manipulation.\r\n\r\nImage source: [Object-Based Affordances Detection with Convolutional Neural Networks and Dense Conditional Random Fields](https://dkanou.github.io/publ/P15__Nguyen_Kanoulas_Caldwell_Tsagarakis__2017__Object-Based_Affordances_Detection_with_Convolutional_Neural_Networks_and__Dense_Conditional_Random_Fields.pdf)\r\n\r\nUnlike other visual or physical properties that mainly describe the object alone, affordances indicate functional interactions of object parts with humans.","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":23,"papers_with_code":13,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/affordance-detection-on-3d-affordancenet","slug":"affordance-detection-on-3d-affordancenet","dataset":"3D AffordanceNet","dataset_url":"/dataset/3d-affordancenet","rows_in_archive":1,"metrics":["AIOU","mAP"],"first_row_in_archive_order":{"model":"DGCNN","paper_title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","paper_url":"/paper/3d-affordancenet-a-benchmark-for-visual","paper_date":"2021-03-30","arxiv_id":"2103.16397","code_links":[{"title":"Gorilla-Lab-SCUT/AffordanceNet","url":"https://github.com/Gorilla-Lab-SCUT/AffordanceNet"}],"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/affordance-detection-on-3d-affordancenet-1","slug":"affordance-detection-on-3d-affordancenet-1","dataset":"3D AffordanceNet Partial View","dataset_url":null,"rows_in_archive":1,"metrics":["AIOU","mAP"],"first_row_in_archive_order":{"model":"DGCNN","paper_title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","paper_url":"/paper/3d-affordancenet-a-benchmark-for-visual","paper_date":"2021-03-30","arxiv_id":"2103.16397","code_links":[{"title":"Gorilla-Lab-SCUT/AffordanceNet","url":"https://github.com/Gorilla-Lab-SCUT/AffordanceNet"}],"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/affordance-detection-on-3d-affordancenet-2","slug":"affordance-detection-on-3d-affordancenet-2","dataset":"3D AffordanceNet Rotate z","dataset_url":null,"rows_in_archive":1,"metrics":["AIOU","mAP"],"first_row_in_archive_order":{"model":"DGCNN","paper_title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","paper_url":"/paper/3d-affordancenet-a-benchmark-for-visual","paper_date":"2021-03-30","arxiv_id":"2103.16397","code_links":[{"title":"Gorilla-Lab-SCUT/AffordanceNet","url":"https://github.com/Gorilla-Lab-SCUT/AffordanceNet"}],"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/affordance-detection-on-3d-affordancenet-3","slug":"affordance-detection-on-3d-affordancenet-3","dataset":"3D AffordanceNet Rotate SO(3)","dataset_url":null,"rows_in_archive":1,"metrics":["AIOU","mAP"],"first_row_in_archive_order":{"model":"DGCNN","paper_title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","paper_url":"/paper/3d-affordancenet-a-benchmark-for-visual","paper_date":"2021-03-30","arxiv_id":"2103.16397","code_links":[{"title":"Gorilla-Lab-SCUT/AffordanceNet","url":"https://github.com/Gorilla-Lab-SCUT/AffordanceNet"}],"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/3d-affordancenet","name":"3D AffordanceNet","full_name":"","num_papers_in_archive":15},{"url":"/dataset/padv2","name":"PADv2","full_name":"Purpose-driven Affordance Dataset v2","num_papers_in_archive":4},{"url":"/dataset/visual-affordance-learning","name":"Visual Affordance Learning","full_name":"","num_papers_in_archive":2}],"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":13,"of":13,"tagged_in_all":23,"items":[{"url":"/paper/phrase-based-affordance-detection-via-cyclic","title":"Phrase-Based Affordance Detection via Cyclic Bilateral Interaction","date":"2022-02-24","arxiv_id":"2202.12076","repositories_listed":4,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/one-shot-affordance-detection","title":"One-Shot Affordance Detection","date":"2021-06-28","arxiv_id":"2106.14747","repositories_listed":2,"syntology":null},{"url":"/paper/affordance-transfer-learning-for-human-object","title":"Affordance Transfer Learning for Human-Object Interaction Detection","date":"2021-04-07","arxiv_id":"2104.02867","repositories_listed":2,"syntology":null},{"url":"/paper/affordancenet-an-end-to-end-deep-learning","title":"AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection","date":"2017-09-21","arxiv_id":"1709.07326","repositories_listed":2,"syntology":null},{"url":"/paper/multi-label-affordance-mapping-from","title":"Multi-label affordance mapping from egocentric vision","date":"2023-09-05","arxiv_id":"2309.02120","repositories_listed":1,"syntology":null},{"url":"/paper/open-vocabulary-affordance-detection-in-3d","title":"Open-Vocabulary Affordance Detection in 3D Point Clouds","date":"2023-03-04","arxiv_id":"2303.02401","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/affordance-detection-with-dynamic-tree","title":"Affordance detection with Dynamic-Tree Capsule Networks","date":"2022-11-09","arxiv_id":"2211.05200","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-object-states-vs-detecting-objects","title":"Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental Study","date":"2021-12-15","arxiv_id":"2112.08281","repositories_listed":1,"syntology":null},{"url":"/paper/one-shot-object-affordance-detection-in-the","title":"One-Shot Object Affordance Detection in the Wild","date":"2021-08-08","arxiv_id":"2108.03658","repositories_listed":1,"syntology":null},{"url":"/paper/3d-affordancenet-a-benchmark-for-visual","title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","date":"2021-03-30","arxiv_id":"2103.16397","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/detecting-robotic-affordances-on-novel","title":"Recognizing Object Affordances to Support Scene Reasoning for Manipulation Tasks","date":"2019-09-12","arxiv_id":"1909.05770","repositories_listed":1,"syntology":null},{"url":"/paper/what-can-i-do-here-leveraging-deep-3d","title":"What can I do here? Leveraging Deep 3D saliency and geometry for fast and scalable multiple affordance detection","date":"2018-12-03","arxiv_id":"1812.00889","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-affordance-detection","title":"Weakly Supervised Affordance Detection","date":"2017-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":3,"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"}}