{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4XS2USWIKILYF5FKRILQSTR2ZB","short_pith_number":"pith:4XS2USWI","schema_version":"1.0","canonical_sha256":"e5e5aa4ac8521782f4aa8a17094e3ac87a14968a5b3306bfd3e2da803b9dc167","source":{"kind":"arxiv","id":"2203.13815","version":1},"attestation_state":"computed","paper":{"title":"Versatile Multi-Modal Pre-Training for Human-Centric Perception","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Liang Pan, Zhongang Cai, Ziwei Liu","submitted_at":"2022-03-25T17:58:29Z","abstract_excerpt":"Human-centric perception plays a vital role in vision and graphics. But their data annotations are prohibitively expensive. Therefore, it is desirable to have a versatile pre-train model that serves as a foundation for data-efficient downstream tasks transfer. To this end, we propose the Human-Centric Multi-Modal Contrastive Learning framework HCMoCo that leverages the multi-modal nature of human data (e.g. RGB, depth, 2D keypoints) for effective representation learning. The objective comes with two main challenges: dense pre-train for multi-modality data, efficient usage of sparse human prior"},"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":"2203.13815","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-25T17:58:29Z","cross_cats_sorted":[],"title_canon_sha256":"c28bdb09d91e7bc27b003f6cef1c9ddc70d05c444187a404b80e6a988b8a5e22","abstract_canon_sha256":"e4e4e38eceea18c066f2f4e5bafb74ff67e881f868562929f008081edce831f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:36.484301Z","signature_b64":"BlLHz7Uq3w8WoqR81VtVsw1Ps5U3m0YNjXH0Vz+KX9hvp+2v/JfR1WJcLfvinwxc9MU1lOe5mdETayssr1O7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5e5aa4ac8521782f4aa8a17094e3ac87a14968a5b3306bfd3e2da803b9dc167","last_reissued_at":"2026-07-05T04:08:36.483913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:36.483913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Versatile Multi-Modal Pre-Training for Human-Centric Perception","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Liang Pan, Zhongang Cai, Ziwei Liu","submitted_at":"2022-03-25T17:58:29Z","abstract_excerpt":"Human-centric perception plays a vital role in vision and graphics. But their data annotations are prohibitively expensive. Therefore, it is desirable to have a versatile pre-train model that serves as a foundation for data-efficient downstream tasks transfer. To this end, we propose the Human-Centric Multi-Modal Contrastive Learning framework HCMoCo that leverages the multi-modal nature of human data (e.g. RGB, depth, 2D keypoints) for effective representation learning. The objective comes with two main challenges: dense pre-train for multi-modality data, efficient usage of sparse human prior"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13815","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/2203.13815/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":"2203.13815","created_at":"2026-07-05T04:08:36.483971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.13815v1","created_at":"2026-07-05T04:08:36.483971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13815","created_at":"2026-07-05T04:08:36.483971+00:00"},{"alias_kind":"pith_short_12","alias_value":"4XS2USWIKILY","created_at":"2026-07-05T04:08:36.483971+00:00"},{"alias_kind":"pith_short_16","alias_value":"4XS2USWIKILYF5FK","created_at":"2026-07-05T04:08:36.483971+00:00"},{"alias_kind":"pith_short_8","alias_value":"4XS2USWI","created_at":"2026-07-05T04:08:36.483971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.05098","citing_title":"Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4XS2USWIKILYF5FKRILQSTR2ZB","json":"https://pith.science/pith/4XS2USWIKILYF5FKRILQSTR2ZB.json","graph_json":"https://pith.science/api/pith-number/4XS2USWIKILYF5FKRILQSTR2ZB/graph.json","events_json":"https://pith.science/api/pith-number/4XS2USWIKILYF5FKRILQSTR2ZB/events.json","paper":"https://pith.science/paper/4XS2USWI"},"agent_actions":{"view_html":"https://pith.science/pith/4XS2USWIKILYF5FKRILQSTR2ZB","download_json":"https://pith.science/pith/4XS2USWIKILYF5FKRILQSTR2ZB.json","view_paper":"https://pith.science/paper/4XS2USWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.13815&json=true","fetch_graph":"https://pith.science/api/pith-number/4XS2USWIKILYF5FKRILQSTR2ZB/graph.json","fetch_events":"https://pith.science/api/pith-number/4XS2USWIKILYF5FKRILQSTR2ZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4XS2USWIKILYF5FKRILQSTR2ZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4XS2USWIKILYF5FKRILQSTR2ZB/action/storage_attestation","attest_author":"https://pith.science/pith/4XS2USWIKILYF5FKRILQSTR2ZB/action/author_attestation","sign_citation":"https://pith.science/pith/4XS2USWIKILYF5FKRILQSTR2ZB/action/citation_signature","submit_replication":"https://pith.science/pith/4XS2USWIKILYF5FKRILQSTR2ZB/action/replication_record"}},"created_at":"2026-07-05T04:08:36.483971+00:00","updated_at":"2026-07-05T04:08:36.483971+00:00"}