{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XC5E7VTVQSKBOWFT4XCOOXKA73","short_pith_number":"pith:XC5E7VTV","schema_version":"1.0","canonical_sha256":"b8ba4fd67584941758b3e5c4e75d40fee6692edccb7cb8293c8f73a7c08bdc2c","source":{"kind":"arxiv","id":"2410.07164","version":1},"attestation_state":"computed","paper":{"title":"AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Han, Kwan-Yee K. Wong, Liang Pan, Yukang Cao, Ziwei Liu","submitted_at":"2024-10-09T17:58:56Z","abstract_excerpt":"Recent advancements in diffusion models have led to significant improvements in the generation and animation of 4D full-body human-object interactions (HOI). Nevertheless, existing methods primarily focus on SMPL-based motion generation, which is limited by the scarcity of realistic large-scale interaction data. This constraint affects their ability to create everyday HOI scenes. This paper addresses this challenge using a zero-shot approach with a pre-trained diffusion model. Despite this potential, achieving our goals is difficult due to the diffusion model's lack of understanding of ''where"},"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":"2410.07164","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:58:56Z","cross_cats_sorted":[],"title_canon_sha256":"59460207a157d9af21cfbbc00c6a90bf8495dc8647559eac213cc963057c8072","abstract_canon_sha256":"3a76ea99a09c0f840eb4267f85bf43780c462755b83d91105cfd44e3cdcef9fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:11.928649Z","signature_b64":"n+TBeysj0Yp9/qTdKSvdcPuvvAtVxecq1IAJ2+mipXhSFxdg9PZ71r5YnliBBoTonJHLTmjbxY3S4tx37c46AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8ba4fd67584941758b3e5c4e75d40fee6692edccb7cb8293c8f73a7c08bdc2c","last_reissued_at":"2026-07-05T09:18:11.928204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:11.928204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Han, Kwan-Yee K. Wong, Liang Pan, Yukang Cao, Ziwei Liu","submitted_at":"2024-10-09T17:58:56Z","abstract_excerpt":"Recent advancements in diffusion models have led to significant improvements in the generation and animation of 4D full-body human-object interactions (HOI). Nevertheless, existing methods primarily focus on SMPL-based motion generation, which is limited by the scarcity of realistic large-scale interaction data. This constraint affects their ability to create everyday HOI scenes. This paper addresses this challenge using a zero-shot approach with a pre-trained diffusion model. Despite this potential, achieving our goals is difficult due to the diffusion model's lack of understanding of ''where"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07164","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.07164/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":"2410.07164","created_at":"2026-07-05T09:18:11.928262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07164v1","created_at":"2026-07-05T09:18:11.928262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07164","created_at":"2026-07-05T09:18:11.928262+00:00"},{"alias_kind":"pith_short_12","alias_value":"XC5E7VTVQSKB","created_at":"2026-07-05T09:18:11.928262+00:00"},{"alias_kind":"pith_short_16","alias_value":"XC5E7VTVQSKBOWFT","created_at":"2026-07-05T09:18:11.928262+00:00"},{"alias_kind":"pith_short_8","alias_value":"XC5E7VTV","created_at":"2026-07-05T09:18:11.928262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30268","citing_title":"PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02736","citing_title":"THOM: Generating Physically Plausible Hand-Object Meshes From Text","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27491","citing_title":"Uni-HOI:A Unified framework for Learning the Joint distribution of Text and Human-Object Interaction","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05756","citing_title":"MaMi-HOI: Harmonizing Global Kinematics and Local Geometry for Human-Object Interaction Generation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XC5E7VTVQSKBOWFT4XCOOXKA73","json":"https://pith.science/pith/XC5E7VTVQSKBOWFT4XCOOXKA73.json","graph_json":"https://pith.science/api/pith-number/XC5E7VTVQSKBOWFT4XCOOXKA73/graph.json","events_json":"https://pith.science/api/pith-number/XC5E7VTVQSKBOWFT4XCOOXKA73/events.json","paper":"https://pith.science/paper/XC5E7VTV"},"agent_actions":{"view_html":"https://pith.science/pith/XC5E7VTVQSKBOWFT4XCOOXKA73","download_json":"https://pith.science/pith/XC5E7VTVQSKBOWFT4XCOOXKA73.json","view_paper":"https://pith.science/paper/XC5E7VTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07164&json=true","fetch_graph":"https://pith.science/api/pith-number/XC5E7VTVQSKBOWFT4XCOOXKA73/graph.json","fetch_events":"https://pith.science/api/pith-number/XC5E7VTVQSKBOWFT4XCOOXKA73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XC5E7VTVQSKBOWFT4XCOOXKA73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XC5E7VTVQSKBOWFT4XCOOXKA73/action/storage_attestation","attest_author":"https://pith.science/pith/XC5E7VTVQSKBOWFT4XCOOXKA73/action/author_attestation","sign_citation":"https://pith.science/pith/XC5E7VTVQSKBOWFT4XCOOXKA73/action/citation_signature","submit_replication":"https://pith.science/pith/XC5E7VTVQSKBOWFT4XCOOXKA73/action/replication_record"}},"created_at":"2026-07-05T09:18:11.928262+00:00","updated_at":"2026-07-05T09:18:11.928262+00:00"}