{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:B5AH4SNDXPQUPGJCOKXJOUFB6L","short_pith_number":"pith:B5AH4SND","schema_version":"1.0","canonical_sha256":"0f407e49a3bbe147992272ae9750a1f2c0a1b1cda7d0a46e15fd21fc1de6eee2","source":{"kind":"arxiv","id":"2211.07501","version":2},"attestation_state":"computed","paper":{"title":"Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cewu Lu, Dongliang Wang, Haisheng Su, Hao-Shu Fang, Hongwei Fan, Liang Xu, Peiyang Guo, Wei Wu, Yiming Dou, Yong-Lu Li, Zuoyu Qiu","submitted_at":"2022-11-14T16:33:54Z","abstract_excerpt":"Spatio-temporal Human-Object Interaction (ST-HOI) detection aims at detecting HOIs from videos, which is crucial for activity understanding. In daily HOIs, humans often interact with a variety of objects, e.g., holding and touching dozens of household items in cleaning. However, existing whole body-object interaction video benchmarks usually provide limited object classes. Here, we introduce a new benchmark based on AVA: Discovering Interacted Objects (DIO) including 51 interactions and 1,000+ objects. Accordingly, an ST-HOI learning task is proposed expecting vision systems to track human act"},"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":"2211.07501","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-14T16:33:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"120e77b23296917e4bab4da01fab3093fb233dd6e671a0ecad0e2dc72f07eef0","abstract_canon_sha256":"a64edb1d39b4d448a3eab1145aa06d4ceac8084653f42aa3dd100ef8b0e76845"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:13.984884Z","signature_b64":"AY+wD2A+EV1tQXnQkHHTllk9RpIeBqxYYLpKwif4bmmVOlSzC3VBLsE2AhYMk9+odawh5T09fGQ6vpBWwjXPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f407e49a3bbe147992272ae9750a1f2c0a1b1cda7d0a46e15fd21fc1de6eee2","last_reissued_at":"2026-07-05T05:17:13.984490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:13.984490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cewu Lu, Dongliang Wang, Haisheng Su, Hao-Shu Fang, Hongwei Fan, Liang Xu, Peiyang Guo, Wei Wu, Yiming Dou, Yong-Lu Li, Zuoyu Qiu","submitted_at":"2022-11-14T16:33:54Z","abstract_excerpt":"Spatio-temporal Human-Object Interaction (ST-HOI) detection aims at detecting HOIs from videos, which is crucial for activity understanding. In daily HOIs, humans often interact with a variety of objects, e.g., holding and touching dozens of household items in cleaning. However, existing whole body-object interaction video benchmarks usually provide limited object classes. Here, we introduce a new benchmark based on AVA: Discovering Interacted Objects (DIO) including 51 interactions and 1,000+ objects. Accordingly, an ST-HOI learning task is proposed expecting vision systems to track human act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07501","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.07501/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2211.07501","created_at":"2026-07-05T05:17:13.984546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.07501v2","created_at":"2026-07-05T05:17:13.984546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07501","created_at":"2026-07-05T05:17:13.984546+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5AH4SNDXPQU","created_at":"2026-07-05T05:17:13.984546+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5AH4SNDXPQUPGJC","created_at":"2026-07-05T05:17:13.984546+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5AH4SND","created_at":"2026-07-05T05:17:13.984546+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/B5AH4SNDXPQUPGJCOKXJOUFB6L","json":"https://pith.science/pith/B5AH4SNDXPQUPGJCOKXJOUFB6L.json","graph_json":"https://pith.science/api/pith-number/B5AH4SNDXPQUPGJCOKXJOUFB6L/graph.json","events_json":"https://pith.science/api/pith-number/B5AH4SNDXPQUPGJCOKXJOUFB6L/events.json","paper":"https://pith.science/paper/B5AH4SND"},"agent_actions":{"view_html":"https://pith.science/pith/B5AH4SNDXPQUPGJCOKXJOUFB6L","download_json":"https://pith.science/pith/B5AH4SNDXPQUPGJCOKXJOUFB6L.json","view_paper":"https://pith.science/paper/B5AH4SND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.07501&json=true","fetch_graph":"https://pith.science/api/pith-number/B5AH4SNDXPQUPGJCOKXJOUFB6L/graph.json","fetch_events":"https://pith.science/api/pith-number/B5AH4SNDXPQUPGJCOKXJOUFB6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5AH4SNDXPQUPGJCOKXJOUFB6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5AH4SNDXPQUPGJCOKXJOUFB6L/action/storage_attestation","attest_author":"https://pith.science/pith/B5AH4SNDXPQUPGJCOKXJOUFB6L/action/author_attestation","sign_citation":"https://pith.science/pith/B5AH4SNDXPQUPGJCOKXJOUFB6L/action/citation_signature","submit_replication":"https://pith.science/pith/B5AH4SNDXPQUPGJCOKXJOUFB6L/action/replication_record"}},"created_at":"2026-07-05T05:17:13.984546+00:00","updated_at":"2026-07-05T05:17:13.984546+00:00"}