{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TF2TZWNCAAPUVYIUFLC37CMKYN","short_pith_number":"pith:TF2TZWNC","schema_version":"1.0","canonical_sha256":"99753cd9a2001f4ae1142ac5bf898ac37077faffdb205e69ee954756ac5148c5","source":{"kind":"arxiv","id":"2412.19542","version":2},"attestation_state":"computed","paper":{"title":"Interacted Object Grounding in Spatio-Temporal Human-Object Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Boran Wen, Cewu Lu, Hongwei Fan, Lizhuang Ma, Xiaoyang Liu, Xinpeng Liu, Yong-Lu Li, Yulong Chen, Zizheng Zhou","submitted_at":"2024-12-27T09:08:46Z","abstract_excerpt":"Spatio-temporal Human-Object Interaction (ST-HOI) understanding aims at detecting HOIs from videos, which is crucial for activity understanding. However, existing whole-body-object interaction video benchmarks overlook the truth that open-world objects are diverse, that is, they usually provide limited and predefined object classes. Therefore, we introduce a new open-world benchmark: Grounding Interacted Objects (GIO) including 1,098 interacted objects class and 290K interacted object boxes annotation. Accordingly, an object grounding task is proposed expecting vision systems to discover inter"},"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":"2412.19542","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T09:08:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bbadf33dbed1a829d157b4edb8d2056f506b9379ed9971acb438e72811239f1d","abstract_canon_sha256":"d531afafab271e405eceadeee12a8d9c01d3b2dff31eb1d28be9be072e77394e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:47.566710Z","signature_b64":"Mq3PmA9kLUtdXcQawR3Gxu7fH8nn0g2F1rNw43CneMkiXVf84pdEQHN+z6PlbDEgiNIPVe6FjnMrIHvjRVteCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99753cd9a2001f4ae1142ac5bf898ac37077faffdb205e69ee954756ac5148c5","last_reissued_at":"2026-07-05T10:18:47.565697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:47.565697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interacted Object Grounding in Spatio-Temporal Human-Object Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Boran Wen, Cewu Lu, Hongwei Fan, Lizhuang Ma, Xiaoyang Liu, Xinpeng Liu, Yong-Lu Li, Yulong Chen, Zizheng Zhou","submitted_at":"2024-12-27T09:08:46Z","abstract_excerpt":"Spatio-temporal Human-Object Interaction (ST-HOI) understanding aims at detecting HOIs from videos, which is crucial for activity understanding. However, existing whole-body-object interaction video benchmarks overlook the truth that open-world objects are diverse, that is, they usually provide limited and predefined object classes. Therefore, we introduce a new open-world benchmark: Grounding Interacted Objects (GIO) including 1,098 interacted objects class and 290K interacted object boxes annotation. Accordingly, an object grounding task is proposed expecting vision systems to discover inter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19542","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/2412.19542/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":"2412.19542","created_at":"2026-07-05T10:18:47.565764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19542v2","created_at":"2026-07-05T10:18:47.565764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19542","created_at":"2026-07-05T10:18:47.565764+00:00"},{"alias_kind":"pith_short_12","alias_value":"TF2TZWNCAAPU","created_at":"2026-07-05T10:18:47.565764+00:00"},{"alias_kind":"pith_short_16","alias_value":"TF2TZWNCAAPUVYIU","created_at":"2026-07-05T10:18:47.565764+00:00"},{"alias_kind":"pith_short_8","alias_value":"TF2TZWNC","created_at":"2026-07-05T10:18:47.565764+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/TF2TZWNCAAPUVYIUFLC37CMKYN","json":"https://pith.science/pith/TF2TZWNCAAPUVYIUFLC37CMKYN.json","graph_json":"https://pith.science/api/pith-number/TF2TZWNCAAPUVYIUFLC37CMKYN/graph.json","events_json":"https://pith.science/api/pith-number/TF2TZWNCAAPUVYIUFLC37CMKYN/events.json","paper":"https://pith.science/paper/TF2TZWNC"},"agent_actions":{"view_html":"https://pith.science/pith/TF2TZWNCAAPUVYIUFLC37CMKYN","download_json":"https://pith.science/pith/TF2TZWNCAAPUVYIUFLC37CMKYN.json","view_paper":"https://pith.science/paper/TF2TZWNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19542&json=true","fetch_graph":"https://pith.science/api/pith-number/TF2TZWNCAAPUVYIUFLC37CMKYN/graph.json","fetch_events":"https://pith.science/api/pith-number/TF2TZWNCAAPUVYIUFLC37CMKYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TF2TZWNCAAPUVYIUFLC37CMKYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TF2TZWNCAAPUVYIUFLC37CMKYN/action/storage_attestation","attest_author":"https://pith.science/pith/TF2TZWNCAAPUVYIUFLC37CMKYN/action/author_attestation","sign_citation":"https://pith.science/pith/TF2TZWNCAAPUVYIUFLC37CMKYN/action/citation_signature","submit_replication":"https://pith.science/pith/TF2TZWNCAAPUVYIUFLC37CMKYN/action/replication_record"}},"created_at":"2026-07-05T10:18:47.565764+00:00","updated_at":"2026-07-05T10:18:47.565764+00:00"}