{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R4SSMXLS2V2OBZ3JKO46VDFB3Q","short_pith_number":"pith:R4SSMXLS","schema_version":"1.0","canonical_sha256":"8f25265d72d574e0e76953b9ea8ca1dc08b2651974c9fb6c9ba5abd596e29c38","source":{"kind":"arxiv","id":"2603.14686","version":2},"attestation_state":"computed","paper":{"title":"MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Zhao, Chuong Nguyen, Hang Zhou, Haocheng Feng, Hongdong Li, Jinbo Wu, Jingdong Wang, Jinguang Tong, Kaisiyuan Wang, Mochu Xiang, Wei He, Xuan Huang, Xuesong Li, Yingying Li, Zhelun Shen","submitted_at":"2026-03-16T00:43:38Z","abstract_excerpt":"Human-Object Interaction (HOI) video reenactment aims to transfer the interaction dynamics of a source video to a novel target object while preserving realistic hand-object coordination. Existing methods typically rely on sparse 2D motion controls and monocular references, which are insufficient for complex out-of-plane motion and large viewpoint changes. We present MVHOI, a two-stage framework combining implicit motion extraction, 3D-aware multi-view reasoning, and video generation. In the first stage, a motion extractor encodes object dynamics into implicit motion descriptors. Conditioned on"},"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":"2603.14686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-16T00:43:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8419b83329cfc3e87a024b0468acafe2e3432c86d638fdd5967bd977924f023f","abstract_canon_sha256":"a3a5b05d92b356347a0af85110d98f8d8258afceb4218e4adc926b68268dc7b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:36:17.990557Z","signature_b64":"yzuCIlpmm5tNzWcW2oIG4dklYot4KMYdA5enVd+HaRb9D/n6r5PgaUo+X/jQACKeRNBncwA78zVJvmUlTPFTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f25265d72d574e0e76953b9ea8ca1dc08b2651974c9fb6c9ba5abd596e29c38","last_reissued_at":"2026-08-04T00:36:17.988797Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:36:17.988797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Zhao, Chuong Nguyen, Hang Zhou, Haocheng Feng, Hongdong Li, Jinbo Wu, Jingdong Wang, Jinguang Tong, Kaisiyuan Wang, Mochu Xiang, Wei He, Xuan Huang, Xuesong Li, Yingying Li, Zhelun Shen","submitted_at":"2026-03-16T00:43:38Z","abstract_excerpt":"Human-Object Interaction (HOI) video reenactment aims to transfer the interaction dynamics of a source video to a novel target object while preserving realistic hand-object coordination. Existing methods typically rely on sparse 2D motion controls and monocular references, which are insufficient for complex out-of-plane motion and large viewpoint changes. We present MVHOI, a two-stage framework combining implicit motion extraction, 3D-aware multi-view reasoning, and video generation. In the first stage, a motion extractor encodes object dynamics into implicit motion descriptors. Conditioned on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14686","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/2603.14686/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":"2603.14686","created_at":"2026-08-04T00:36:17.990067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.14686v2","created_at":"2026-08-04T00:36:17.990067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14686","created_at":"2026-08-04T00:36:17.990067+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4SSMXLS2V2O","created_at":"2026-08-04T00:36:17.990067+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4SSMXLS2V2OBZ3J","created_at":"2026-08-04T00:36:17.990067+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4SSMXLS","created_at":"2026-08-04T00:36:17.990067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.24498","citing_title":"VistaRef: Boosting Visual Spatial Orientation Awareness for Pointing-to-Object Detection","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14556","citing_title":"Controllable Video Object Insertion via Multiview Priors","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4SSMXLS2V2OBZ3JKO46VDFB3Q","json":"https://pith.science/pith/R4SSMXLS2V2OBZ3JKO46VDFB3Q.json","graph_json":"https://pith.science/api/pith-number/R4SSMXLS2V2OBZ3JKO46VDFB3Q/graph.json","events_json":"https://pith.science/api/pith-number/R4SSMXLS2V2OBZ3JKO46VDFB3Q/events.json","paper":"https://pith.science/paper/R4SSMXLS"},"agent_actions":{"view_html":"https://pith.science/pith/R4SSMXLS2V2OBZ3JKO46VDFB3Q","download_json":"https://pith.science/pith/R4SSMXLS2V2OBZ3JKO46VDFB3Q.json","view_paper":"https://pith.science/paper/R4SSMXLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.14686&json=true","fetch_graph":"https://pith.science/api/pith-number/R4SSMXLS2V2OBZ3JKO46VDFB3Q/graph.json","fetch_events":"https://pith.science/api/pith-number/R4SSMXLS2V2OBZ3JKO46VDFB3Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4SSMXLS2V2OBZ3JKO46VDFB3Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4SSMXLS2V2OBZ3JKO46VDFB3Q/action/storage_attestation","attest_author":"https://pith.science/pith/R4SSMXLS2V2OBZ3JKO46VDFB3Q/action/author_attestation","sign_citation":"https://pith.science/pith/R4SSMXLS2V2OBZ3JKO46VDFB3Q/action/citation_signature","submit_replication":"https://pith.science/pith/R4SSMXLS2V2OBZ3JKO46VDFB3Q/action/replication_record"}},"created_at":"2026-08-04T00:36:17.990067+00:00","updated_at":"2026-08-04T00:36:17.990067+00:00"}