{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QZDVAWVGBVQEST7ID5KZU522W5","short_pith_number":"pith:QZDVAWVG","schema_version":"1.0","canonical_sha256":"8647505aa60d60494fe81f559a775ab742489b23635b9ee685d8fc665033b810","source":{"kind":"arxiv","id":"1703.00503","version":1},"attestation_state":"computed","paper":{"title":"Learning Social Affordance Grammar from Videos: Transferring Human Interactions to Human-Robot Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Michael S. Ryoo, Song-Chun Zhu, Tianmin Shu, Xiaofeng Gao","submitted_at":"2017-03-01T21:05:10Z","abstract_excerpt":"In this paper, we present a general framework for learning social affordance grammar as a spatiotemporal AND-OR graph (ST-AOG) from RGB-D videos of human interactions, and transfer the grammar to humanoids to enable a real-time motion inference for human-robot interaction (HRI). Based on Gibbs sampling, our weakly supervised grammar learning can automatically construct a hierarchical representation of an interaction with long-term joint sub-tasks of both agents and short term atomic actions of individual agents. Based on a new RGB-D video dataset with rich instances of human interactions, our "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1703.00503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-01T21:05:10Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"289aafcbf9d8ef0b0402fee7c846549b42c6e52752ac25bc159027368d7b6c85","abstract_canon_sha256":"f520ef9cdfff183994a0645c8bb78884977c02d791e3b31b910b06066538027a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:41.499887Z","signature_b64":"PArVU8qXPWfA3nfrf21BgrA2qcbkl+qZUufVavtRbPKWC/hZvX8t23O2MJ3q0qG5FJaS7hx54IgQJxY0PSsdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8647505aa60d60494fe81f559a775ab742489b23635b9ee685d8fc665033b810","last_reissued_at":"2026-05-18T00:49:41.499259Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:41.499259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Social Affordance Grammar from Videos: Transferring Human Interactions to Human-Robot Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Michael S. Ryoo, Song-Chun Zhu, Tianmin Shu, Xiaofeng Gao","submitted_at":"2017-03-01T21:05:10Z","abstract_excerpt":"In this paper, we present a general framework for learning social affordance grammar as a spatiotemporal AND-OR graph (ST-AOG) from RGB-D videos of human interactions, and transfer the grammar to humanoids to enable a real-time motion inference for human-robot interaction (HRI). Based on Gibbs sampling, our weakly supervised grammar learning can automatically construct a hierarchical representation of an interaction with long-term joint sub-tasks of both agents and short term atomic actions of individual agents. Based on a new RGB-D video dataset with rich instances of human interactions, our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00503","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1703.00503","created_at":"2026-05-18T00:49:41.499358+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00503v1","created_at":"2026-05-18T00:49:41.499358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00503","created_at":"2026-05-18T00:49:41.499358+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZDVAWVGBVQE","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZDVAWVGBVQEST7I","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZDVAWVG","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZDVAWVGBVQEST7ID5KZU522W5","json":"https://pith.science/pith/QZDVAWVGBVQEST7ID5KZU522W5.json","graph_json":"https://pith.science/api/pith-number/QZDVAWVGBVQEST7ID5KZU522W5/graph.json","events_json":"https://pith.science/api/pith-number/QZDVAWVGBVQEST7ID5KZU522W5/events.json","paper":"https://pith.science/paper/QZDVAWVG"},"agent_actions":{"view_html":"https://pith.science/pith/QZDVAWVGBVQEST7ID5KZU522W5","download_json":"https://pith.science/pith/QZDVAWVGBVQEST7ID5KZU522W5.json","view_paper":"https://pith.science/paper/QZDVAWVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00503&json=true","fetch_graph":"https://pith.science/api/pith-number/QZDVAWVGBVQEST7ID5KZU522W5/graph.json","fetch_events":"https://pith.science/api/pith-number/QZDVAWVGBVQEST7ID5KZU522W5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZDVAWVGBVQEST7ID5KZU522W5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZDVAWVGBVQEST7ID5KZU522W5/action/storage_attestation","attest_author":"https://pith.science/pith/QZDVAWVGBVQEST7ID5KZU522W5/action/author_attestation","sign_citation":"https://pith.science/pith/QZDVAWVGBVQEST7ID5KZU522W5/action/citation_signature","submit_replication":"https://pith.science/pith/QZDVAWVGBVQEST7ID5KZU522W5/action/replication_record"}},"created_at":"2026-05-18T00:49:41.499358+00:00","updated_at":"2026-05-18T00:49:41.499358+00:00"}