{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RVU32RYQ3AVGFHJOBZ4TUF3NMG","short_pith_number":"pith:RVU32RYQ","schema_version":"1.0","canonical_sha256":"8d69bd4710d82a629d2e0e793a176d61b6f36ddf0d630bd63b426e697724759c","source":{"kind":"arxiv","id":"1908.05293","version":3},"attestation_state":"computed","paper":{"title":"Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Sharma, Arjun Jain, Nitesh B. Gundavarapu, Rahul Mitra","submitted_at":"2019-08-14T18:13:57Z","abstract_excerpt":"The best performing methods for 3D human pose estimation from monocular images require large amounts of in-the-wild 2D and controlled 3D pose annotated datasets which are costly and require sophisticated systems to acquire. To reduce this annotation dependency, we propose Multiview-Consistent Semi Supervised Learning (MCSS) framework that utilizes similarity in pose information from unannotated, uncalibrated but synchronized multi-view videos of human motions as additional weak supervision signal to guide 3D human pose regression. Our framework applies hard-negative mining based on temporal re"},"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":"1908.05293","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-08-14T18:13:57Z","cross_cats_sorted":[],"title_canon_sha256":"397ded373b530ee703d2cd5214fd7a95478774e717d93b7a14c0aa3dcfbced15","abstract_canon_sha256":"83414e662a618715a439065fbdc8c0f3154266a29bd5c25f5e4b018336ea741b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:19.682855Z","signature_b64":"xhV0z++aUwjtNbRadmva2CclnjgBOpR6+JXe7KTQGAOjOS046DnnAlutRhJh+Uu8y9b5St0B+O6+k1lB+x5JDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d69bd4710d82a629d2e0e793a176d61b6f36ddf0d630bd63b426e697724759c","last_reissued_at":"2026-07-05T00:43:19.682407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:19.682407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Sharma, Arjun Jain, Nitesh B. Gundavarapu, Rahul Mitra","submitted_at":"2019-08-14T18:13:57Z","abstract_excerpt":"The best performing methods for 3D human pose estimation from monocular images require large amounts of in-the-wild 2D and controlled 3D pose annotated datasets which are costly and require sophisticated systems to acquire. To reduce this annotation dependency, we propose Multiview-Consistent Semi Supervised Learning (MCSS) framework that utilizes similarity in pose information from unannotated, uncalibrated but synchronized multi-view videos of human motions as additional weak supervision signal to guide 3D human pose regression. Our framework applies hard-negative mining based on temporal re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05293","kind":"arxiv","version":3},"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/1908.05293/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":"1908.05293","created_at":"2026-07-05T00:43:19.682470+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05293v3","created_at":"2026-07-05T00:43:19.682470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05293","created_at":"2026-07-05T00:43:19.682470+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVU32RYQ3AVG","created_at":"2026-07-05T00:43:19.682470+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVU32RYQ3AVGFHJO","created_at":"2026-07-05T00:43:19.682470+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVU32RYQ","created_at":"2026-07-05T00:43:19.682470+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/RVU32RYQ3AVGFHJOBZ4TUF3NMG","json":"https://pith.science/pith/RVU32RYQ3AVGFHJOBZ4TUF3NMG.json","graph_json":"https://pith.science/api/pith-number/RVU32RYQ3AVGFHJOBZ4TUF3NMG/graph.json","events_json":"https://pith.science/api/pith-number/RVU32RYQ3AVGFHJOBZ4TUF3NMG/events.json","paper":"https://pith.science/paper/RVU32RYQ"},"agent_actions":{"view_html":"https://pith.science/pith/RVU32RYQ3AVGFHJOBZ4TUF3NMG","download_json":"https://pith.science/pith/RVU32RYQ3AVGFHJOBZ4TUF3NMG.json","view_paper":"https://pith.science/paper/RVU32RYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05293&json=true","fetch_graph":"https://pith.science/api/pith-number/RVU32RYQ3AVGFHJOBZ4TUF3NMG/graph.json","fetch_events":"https://pith.science/api/pith-number/RVU32RYQ3AVGFHJOBZ4TUF3NMG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVU32RYQ3AVGFHJOBZ4TUF3NMG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVU32RYQ3AVGFHJOBZ4TUF3NMG/action/storage_attestation","attest_author":"https://pith.science/pith/RVU32RYQ3AVGFHJOBZ4TUF3NMG/action/author_attestation","sign_citation":"https://pith.science/pith/RVU32RYQ3AVGFHJOBZ4TUF3NMG/action/citation_signature","submit_replication":"https://pith.science/pith/RVU32RYQ3AVGFHJOBZ4TUF3NMG/action/replication_record"}},"created_at":"2026-07-05T00:43:19.682470+00:00","updated_at":"2026-07-05T00:43:19.682470+00:00"}