{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AEZ7E7R7IDZHUICOD25Q5D2AAY","short_pith_number":"pith:AEZ7E7R7","schema_version":"1.0","canonical_sha256":"0133f27e3f40f27a204e1ebb0e8f40061d5cc4aadcfdc00deff9e3931ffcd1bf","source":{"kind":"arxiv","id":"2302.11306","version":2},"attestation_state":"computed","paper":{"title":"Human MotionFormer: Transferring Human Motions with Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengbin Jin, Faqiang Wang, Haoye Dong, Hongyu Liu, Huawei Wei, Jia Xu, Lihui Qian, Qifeng Chen, Xintong Han, Yibing Song, Zhe Lin","submitted_at":"2023-02-22T11:42:44Z","abstract_excerpt":"Human motion transfer aims to transfer motions from a target dynamic person to a source static one for motion synthesis. An accurate matching between the source person and the target motion in both large and subtle motion changes is vital for improving the transferred motion quality. In this paper, we propose Human MotionFormer, a hierarchical ViT framework that leverages global and local perceptions to capture large and subtle motion matching, respectively. It consists of two ViT encoders to extract input features (i.e., a target motion image and a source human image) and a ViT decoder with s"},"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":"2302.11306","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-22T11:42:44Z","cross_cats_sorted":[],"title_canon_sha256":"58ff757cdafc693d73c57aa66aa8e6f4ecf6a551d34c8074c8fe59868d8859f0","abstract_canon_sha256":"4e2965c1956dbe5b28e86776df48cb1443649271bd3b69431ed12b741ce228bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:39.396306Z","signature_b64":"y8flNmX4WisNh2eDbd5bopcUdG1wG8Owe/d3XRTmojm7D4kLu37tEdxIRJzKhNMgk4cvW5RAb3PtU3WJFIteDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0133f27e3f40f27a204e1ebb0e8f40061d5cc4aadcfdc00deff9e3931ffcd1bf","last_reissued_at":"2026-07-05T05:45:39.395841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:39.395841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human MotionFormer: Transferring Human Motions with Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengbin Jin, Faqiang Wang, Haoye Dong, Hongyu Liu, Huawei Wei, Jia Xu, Lihui Qian, Qifeng Chen, Xintong Han, Yibing Song, Zhe Lin","submitted_at":"2023-02-22T11:42:44Z","abstract_excerpt":"Human motion transfer aims to transfer motions from a target dynamic person to a source static one for motion synthesis. An accurate matching between the source person and the target motion in both large and subtle motion changes is vital for improving the transferred motion quality. In this paper, we propose Human MotionFormer, a hierarchical ViT framework that leverages global and local perceptions to capture large and subtle motion matching, respectively. It consists of two ViT encoders to extract input features (i.e., a target motion image and a source human image) and a ViT decoder with s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11306","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/2302.11306/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":"2302.11306","created_at":"2026-07-05T05:45:39.395898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.11306v2","created_at":"2026-07-05T05:45:39.395898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11306","created_at":"2026-07-05T05:45:39.395898+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEZ7E7R7IDZH","created_at":"2026-07-05T05:45:39.395898+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEZ7E7R7IDZHUICO","created_at":"2026-07-05T05:45:39.395898+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEZ7E7R7","created_at":"2026-07-05T05:45:39.395898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.07603","citing_title":"UIKA: Fast Universal Head Avatar from Pose-Free Images","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04787","citing_title":"AvatarPointillist: AutoRegressive 4D Gaussian Avatarization","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AEZ7E7R7IDZHUICOD25Q5D2AAY","json":"https://pith.science/pith/AEZ7E7R7IDZHUICOD25Q5D2AAY.json","graph_json":"https://pith.science/api/pith-number/AEZ7E7R7IDZHUICOD25Q5D2AAY/graph.json","events_json":"https://pith.science/api/pith-number/AEZ7E7R7IDZHUICOD25Q5D2AAY/events.json","paper":"https://pith.science/paper/AEZ7E7R7"},"agent_actions":{"view_html":"https://pith.science/pith/AEZ7E7R7IDZHUICOD25Q5D2AAY","download_json":"https://pith.science/pith/AEZ7E7R7IDZHUICOD25Q5D2AAY.json","view_paper":"https://pith.science/paper/AEZ7E7R7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.11306&json=true","fetch_graph":"https://pith.science/api/pith-number/AEZ7E7R7IDZHUICOD25Q5D2AAY/graph.json","fetch_events":"https://pith.science/api/pith-number/AEZ7E7R7IDZHUICOD25Q5D2AAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEZ7E7R7IDZHUICOD25Q5D2AAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEZ7E7R7IDZHUICOD25Q5D2AAY/action/storage_attestation","attest_author":"https://pith.science/pith/AEZ7E7R7IDZHUICOD25Q5D2AAY/action/author_attestation","sign_citation":"https://pith.science/pith/AEZ7E7R7IDZHUICOD25Q5D2AAY/action/citation_signature","submit_replication":"https://pith.science/pith/AEZ7E7R7IDZHUICOD25Q5D2AAY/action/replication_record"}},"created_at":"2026-07-05T05:45:39.395898+00:00","updated_at":"2026-07-05T05:45:39.395898+00:00"}