{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SXMHT435GAJTOKBDXMT42UBOKR","short_pith_number":"pith:SXMHT435","schema_version":"1.0","canonical_sha256":"95d879f37d3013372823bb27cd502e546cd4bb8ee5f9d38efff48019cd8eafda","source":{"kind":"arxiv","id":"2301.10900","version":2},"attestation_state":"computed","paper":{"title":"Graph Contrastive Learning for Skeleton-based Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Feng, Errui Ding, Haocheng Feng, Hao Zhou, Jian Wang, Jingdong Wang, Junyu Han, Wenyu Liu, Xiaohu Huang, Xinggang Wang","submitted_at":"2023-01-26T02:09:16Z","abstract_excerpt":"In the field of skeleton-based action recognition, current top-performing graph convolutional networks (GCNs) exploit intra-sequence context to construct adaptive graphs for feature aggregation. However, we argue that such context is still \\textit{local} since the rich cross-sequence relations have not been explicitly investigated. In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\\textit{SkeletonGCL}) to explore the \\textit{global} context across all sequences. In specific, SkeletonGCL associates graph learning across sequences by enforcin"},"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":"2301.10900","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-26T02:09:16Z","cross_cats_sorted":[],"title_canon_sha256":"07635de0563c4b0689ab62b6011b9c061ca1d0e716a92a26d7d8009b1932a030","abstract_canon_sha256":"4e653e0d2fc8f4c77106f23a68baa0be5f6a0be5af7d12f92196fcc5189842d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:18.076233Z","signature_b64":"laLMyfqk+67Q7TaOKaH28zIc4S6CM87xPbY32OKOhQSEzNTE20rW6gm7ic02WzuP7TEALmb9UfRxBxaWYTmrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95d879f37d3013372823bb27cd502e546cd4bb8ee5f9d38efff48019cd8eafda","last_reissued_at":"2026-07-05T06:19:18.075779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:18.075779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Contrastive Learning for Skeleton-based Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Feng, Errui Ding, Haocheng Feng, Hao Zhou, Jian Wang, Jingdong Wang, Junyu Han, Wenyu Liu, Xiaohu Huang, Xinggang Wang","submitted_at":"2023-01-26T02:09:16Z","abstract_excerpt":"In the field of skeleton-based action recognition, current top-performing graph convolutional networks (GCNs) exploit intra-sequence context to construct adaptive graphs for feature aggregation. However, we argue that such context is still \\textit{local} since the rich cross-sequence relations have not been explicitly investigated. In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\\textit{SkeletonGCL}) to explore the \\textit{global} context across all sequences. In specific, SkeletonGCL associates graph learning across sequences by enforcin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10900","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/2301.10900/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":"2301.10900","created_at":"2026-07-05T06:19:18.075838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.10900v2","created_at":"2026-07-05T06:19:18.075838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10900","created_at":"2026-07-05T06:19:18.075838+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXMHT435GAJT","created_at":"2026-07-05T06:19:18.075838+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXMHT435GAJTOKBD","created_at":"2026-07-05T06:19:18.075838+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXMHT435","created_at":"2026-07-05T06:19:18.075838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17013","citing_title":"Towards Universal Skeleton-Based Action Recognition","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17090","citing_title":"Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SXMHT435GAJTOKBDXMT42UBOKR","json":"https://pith.science/pith/SXMHT435GAJTOKBDXMT42UBOKR.json","graph_json":"https://pith.science/api/pith-number/SXMHT435GAJTOKBDXMT42UBOKR/graph.json","events_json":"https://pith.science/api/pith-number/SXMHT435GAJTOKBDXMT42UBOKR/events.json","paper":"https://pith.science/paper/SXMHT435"},"agent_actions":{"view_html":"https://pith.science/pith/SXMHT435GAJTOKBDXMT42UBOKR","download_json":"https://pith.science/pith/SXMHT435GAJTOKBDXMT42UBOKR.json","view_paper":"https://pith.science/paper/SXMHT435","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.10900&json=true","fetch_graph":"https://pith.science/api/pith-number/SXMHT435GAJTOKBDXMT42UBOKR/graph.json","fetch_events":"https://pith.science/api/pith-number/SXMHT435GAJTOKBDXMT42UBOKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXMHT435GAJTOKBDXMT42UBOKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXMHT435GAJTOKBDXMT42UBOKR/action/storage_attestation","attest_author":"https://pith.science/pith/SXMHT435GAJTOKBDXMT42UBOKR/action/author_attestation","sign_citation":"https://pith.science/pith/SXMHT435GAJTOKBDXMT42UBOKR/action/citation_signature","submit_replication":"https://pith.science/pith/SXMHT435GAJTOKBDXMT42UBOKR/action/replication_record"}},"created_at":"2026-07-05T06:19:18.075838+00:00","updated_at":"2026-07-05T06:19:18.075838+00:00"}