{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:P36VYXO5H4URWZ46W5HWJS2TLK","short_pith_number":"pith:P36VYXO5","schema_version":"1.0","canonical_sha256":"7efd5c5ddd3f291b679eb74f64cb535a8ed57192373c585a1bffd799d4fcd01c","source":{"kind":"arxiv","id":"1809.07217","version":2},"attestation_state":"computed","paper":{"title":"3D Human Pose Estimation with Siamese Equivariant Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andr\\'as L\\H{o}rincz, M\\'arton V\\'eges, Viktor Varga","submitted_at":"2018-09-19T14:26:14Z","abstract_excerpt":"In monocular 3D human pose estimation a common setup is to first detect 2D positions and then lift the detection into 3D coordinates. Many algorithms suffer from overfitting to camera positions in the training set. We propose a siamese architecture that learns a rotation equivariant hidden representation to reduce the need for data augmentation. Our method is evaluated on multiple databases with different base networks and shows a consistent improvement of error metrics. It achieves state-of-the-art cross-camera error rate among algorithms that use estimated 2D joint coordinates only."},"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":"1809.07217","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-19T14:26:14Z","cross_cats_sorted":[],"title_canon_sha256":"58f275ed0475bb02b67c70f169184d5d5a3240d1542668608c66f68dcedd9fd4","abstract_canon_sha256":"62ab01112236972c9bd8e2db38b89e306742fb830a8188cfc92edfc5f44b6c8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:50.759242Z","signature_b64":"EHXyWZRG9tLyezBGVV03Mbn+XYv5/XNwlp5flXKFLJySsyWtuy53zyfKnDD8j7k4TXMJCOZyoRfmwhjZS6OrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7efd5c5ddd3f291b679eb74f64cb535a8ed57192373c585a1bffd799d4fcd01c","last_reissued_at":"2026-05-17T23:53:50.758412Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:50.758412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Human Pose Estimation with Siamese Equivariant Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andr\\'as L\\H{o}rincz, M\\'arton V\\'eges, Viktor Varga","submitted_at":"2018-09-19T14:26:14Z","abstract_excerpt":"In monocular 3D human pose estimation a common setup is to first detect 2D positions and then lift the detection into 3D coordinates. Many algorithms suffer from overfitting to camera positions in the training set. We propose a siamese architecture that learns a rotation equivariant hidden representation to reduce the need for data augmentation. Our method is evaluated on multiple databases with different base networks and shows a consistent improvement of error metrics. It achieves state-of-the-art cross-camera error rate among algorithms that use estimated 2D joint coordinates only."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07217","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":""},"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":"1809.07217","created_at":"2026-05-17T23:53:50.758538+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.07217v2","created_at":"2026-05-17T23:53:50.758538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07217","created_at":"2026-05-17T23:53:50.758538+00:00"},{"alias_kind":"pith_short_12","alias_value":"P36VYXO5H4UR","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"P36VYXO5H4URWZ46","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"P36VYXO5","created_at":"2026-05-18T12:32:43.782077+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/P36VYXO5H4URWZ46W5HWJS2TLK","json":"https://pith.science/pith/P36VYXO5H4URWZ46W5HWJS2TLK.json","graph_json":"https://pith.science/api/pith-number/P36VYXO5H4URWZ46W5HWJS2TLK/graph.json","events_json":"https://pith.science/api/pith-number/P36VYXO5H4URWZ46W5HWJS2TLK/events.json","paper":"https://pith.science/paper/P36VYXO5"},"agent_actions":{"view_html":"https://pith.science/pith/P36VYXO5H4URWZ46W5HWJS2TLK","download_json":"https://pith.science/pith/P36VYXO5H4URWZ46W5HWJS2TLK.json","view_paper":"https://pith.science/paper/P36VYXO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.07217&json=true","fetch_graph":"https://pith.science/api/pith-number/P36VYXO5H4URWZ46W5HWJS2TLK/graph.json","fetch_events":"https://pith.science/api/pith-number/P36VYXO5H4URWZ46W5HWJS2TLK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P36VYXO5H4URWZ46W5HWJS2TLK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P36VYXO5H4URWZ46W5HWJS2TLK/action/storage_attestation","attest_author":"https://pith.science/pith/P36VYXO5H4URWZ46W5HWJS2TLK/action/author_attestation","sign_citation":"https://pith.science/pith/P36VYXO5H4URWZ46W5HWJS2TLK/action/citation_signature","submit_replication":"https://pith.science/pith/P36VYXO5H4URWZ46W5HWJS2TLK/action/replication_record"}},"created_at":"2026-05-17T23:53:50.758538+00:00","updated_at":"2026-05-17T23:53:50.758538+00:00"}