{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TFIAXPUNKFZVPJVKKQJ4WEM27Z","short_pith_number":"pith:TFIAXPUN","schema_version":"1.0","canonical_sha256":"99500bbe8d517357a6aa5413cb119afe445802ec75eead16caf08bb1958d79cc","source":{"kind":"arxiv","id":"2106.05953","version":5},"attestation_state":"computed","paper":{"title":"PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian Spurr, Aneesh Dahiya, Otmar Hilliges, Xi Wang, Xucong Zhang","submitted_at":"2021-06-10T17:48:57Z","abstract_excerpt":"Encouraged by the success of contrastive learning on image classification tasks, we propose a new self-supervised method for the structured regression task of 3D hand pose estimation. Contrastive learning makes use of unlabeled data for the purpose of representation learning via a loss formulation that encourages the learned feature representations to be invariant under any image transformation. For 3D hand pose estimation, it too is desirable to have invariance to appearance transformation such as color jitter. However, the task requires equivariance under affine transformations, such as rota"},"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":"2106.05953","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-10T17:48:57Z","cross_cats_sorted":[],"title_canon_sha256":"22cea68ad016ce7b20a8007f811ec99162c4ffed69069ac96bc8ffcbd40a970a","abstract_canon_sha256":"ced447eee842b88fe5402da7459d7eb0402a53b0981c8d1b6c92c024c255b4be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:46.111598Z","signature_b64":"XJWyuXCp1WKSWHiAcEyJdy0ef2cIFiAJ0krbSbznzu1aH5IHeSj+LnxFekiO+bOAmzsiQdcNP1TjYiPW0XqcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99500bbe8d517357a6aa5413cb119afe445802ec75eead16caf08bb1958d79cc","last_reissued_at":"2026-07-05T04:45:46.111248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:46.111248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian Spurr, Aneesh Dahiya, Otmar Hilliges, Xi Wang, Xucong Zhang","submitted_at":"2021-06-10T17:48:57Z","abstract_excerpt":"Encouraged by the success of contrastive learning on image classification tasks, we propose a new self-supervised method for the structured regression task of 3D hand pose estimation. Contrastive learning makes use of unlabeled data for the purpose of representation learning via a loss formulation that encourages the learned feature representations to be invariant under any image transformation. For 3D hand pose estimation, it too is desirable to have invariance to appearance transformation such as color jitter. However, the task requires equivariance under affine transformations, such as rota"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05953","kind":"arxiv","version":5},"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/2106.05953/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":"2106.05953","created_at":"2026-07-05T04:45:46.111303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.05953v5","created_at":"2026-07-05T04:45:46.111303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05953","created_at":"2026-07-05T04:45:46.111303+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFIAXPUNKFZV","created_at":"2026-07-05T04:45:46.111303+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFIAXPUNKFZVPJVK","created_at":"2026-07-05T04:45:46.111303+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFIAXPUN","created_at":"2026-07-05T04:45:46.111303+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/TFIAXPUNKFZVPJVKKQJ4WEM27Z","json":"https://pith.science/pith/TFIAXPUNKFZVPJVKKQJ4WEM27Z.json","graph_json":"https://pith.science/api/pith-number/TFIAXPUNKFZVPJVKKQJ4WEM27Z/graph.json","events_json":"https://pith.science/api/pith-number/TFIAXPUNKFZVPJVKKQJ4WEM27Z/events.json","paper":"https://pith.science/paper/TFIAXPUN"},"agent_actions":{"view_html":"https://pith.science/pith/TFIAXPUNKFZVPJVKKQJ4WEM27Z","download_json":"https://pith.science/pith/TFIAXPUNKFZVPJVKKQJ4WEM27Z.json","view_paper":"https://pith.science/paper/TFIAXPUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.05953&json=true","fetch_graph":"https://pith.science/api/pith-number/TFIAXPUNKFZVPJVKKQJ4WEM27Z/graph.json","fetch_events":"https://pith.science/api/pith-number/TFIAXPUNKFZVPJVKKQJ4WEM27Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFIAXPUNKFZVPJVKKQJ4WEM27Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFIAXPUNKFZVPJVKKQJ4WEM27Z/action/storage_attestation","attest_author":"https://pith.science/pith/TFIAXPUNKFZVPJVKKQJ4WEM27Z/action/author_attestation","sign_citation":"https://pith.science/pith/TFIAXPUNKFZVPJVKKQJ4WEM27Z/action/citation_signature","submit_replication":"https://pith.science/pith/TFIAXPUNKFZVPJVKKQJ4WEM27Z/action/replication_record"}},"created_at":"2026-07-05T04:45:46.111303+00:00","updated_at":"2026-07-05T04:45:46.111303+00:00"}