{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DZ6YXJNTW2N7SYRUQTZBEIH7S5","short_pith_number":"pith:DZ6YXJNT","schema_version":"1.0","canonical_sha256":"1e7d8ba5b3b69bf9623484f21220ff9773b660da1ba91a1e6effe542acc340f0","source":{"kind":"arxiv","id":"2412.09220","version":2},"attestation_state":"computed","paper":{"title":"USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guosen Xie, Hongsong Wang, Junbo Wang, Lei He, Wanjiang Weng","submitted_at":"2024-12-12T12:20:27Z","abstract_excerpt":"Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating additional momentum encoder and memory bank to get negative samples, which increases the difficulty of model training. Furthermore, these methods primarily concentrate on learning a global representation for recognition and retrieval tasks, while overlooking the rich and detailed local representations that are crucial for dense prediction tasks. To alleviate these issues, we introduce a Unified Skeleton-based Dense R"},"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":"2412.09220","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T12:20:27Z","cross_cats_sorted":[],"title_canon_sha256":"867a2a0d67cee21490a8c6149dfd63df39cbcc8f07496e7d30922b97a435787b","abstract_canon_sha256":"36f656aadfc30d93db22c7a149ab07fc34d877357dd001ea528125a194b682e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:14.551324Z","signature_b64":"7MYzaM2Tf4qjWx8Zfz0GKKec8+x7bxRMS/qQZbAraJtBwqt0TAcGEnIEwoeyEoD7kBtsXv2jxZDFRSY/SQ+uDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e7d8ba5b3b69bf9623484f21220ff9773b660da1ba91a1e6effe542acc340f0","last_reissued_at":"2026-07-05T09:49:14.550855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:14.550855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guosen Xie, Hongsong Wang, Junbo Wang, Lei He, Wanjiang Weng","submitted_at":"2024-12-12T12:20:27Z","abstract_excerpt":"Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating additional momentum encoder and memory bank to get negative samples, which increases the difficulty of model training. Furthermore, these methods primarily concentrate on learning a global representation for recognition and retrieval tasks, while overlooking the rich and detailed local representations that are crucial for dense prediction tasks. To alleviate these issues, we introduce a Unified Skeleton-based Dense R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09220","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/2412.09220/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":"2412.09220","created_at":"2026-07-05T09:49:14.550912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09220v2","created_at":"2026-07-05T09:49:14.550912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09220","created_at":"2026-07-05T09:49:14.550912+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZ6YXJNTW2N7","created_at":"2026-07-05T09:49:14.550912+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZ6YXJNTW2N7SYRU","created_at":"2026-07-05T09:49:14.550912+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZ6YXJNT","created_at":"2026-07-05T09:49:14.550912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11450","citing_title":"Exploring Adaptive Masked Reconstruction for Self-Supervised Skeleton-Based Action Recognition","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZ6YXJNTW2N7SYRUQTZBEIH7S5","json":"https://pith.science/pith/DZ6YXJNTW2N7SYRUQTZBEIH7S5.json","graph_json":"https://pith.science/api/pith-number/DZ6YXJNTW2N7SYRUQTZBEIH7S5/graph.json","events_json":"https://pith.science/api/pith-number/DZ6YXJNTW2N7SYRUQTZBEIH7S5/events.json","paper":"https://pith.science/paper/DZ6YXJNT"},"agent_actions":{"view_html":"https://pith.science/pith/DZ6YXJNTW2N7SYRUQTZBEIH7S5","download_json":"https://pith.science/pith/DZ6YXJNTW2N7SYRUQTZBEIH7S5.json","view_paper":"https://pith.science/paper/DZ6YXJNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09220&json=true","fetch_graph":"https://pith.science/api/pith-number/DZ6YXJNTW2N7SYRUQTZBEIH7S5/graph.json","fetch_events":"https://pith.science/api/pith-number/DZ6YXJNTW2N7SYRUQTZBEIH7S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZ6YXJNTW2N7SYRUQTZBEIH7S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZ6YXJNTW2N7SYRUQTZBEIH7S5/action/storage_attestation","attest_author":"https://pith.science/pith/DZ6YXJNTW2N7SYRUQTZBEIH7S5/action/author_attestation","sign_citation":"https://pith.science/pith/DZ6YXJNTW2N7SYRUQTZBEIH7S5/action/citation_signature","submit_replication":"https://pith.science/pith/DZ6YXJNTW2N7SYRUQTZBEIH7S5/action/replication_record"}},"created_at":"2026-07-05T09:49:14.550912+00:00","updated_at":"2026-07-05T09:49:14.550912+00:00"}