{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3GQCVL7MMRKERPPUK4QWVSBHPE","short_pith_number":"pith:3GQCVL7M","schema_version":"1.0","canonical_sha256":"d9a02aafec645448bdf457216ac827793657e788adda746581272cbed9e0b351","source":{"kind":"arxiv","id":"2108.04536","version":1},"attestation_state":"computed","paper":{"title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Desen Zhou, Errui Ding, Jian Wang, Shidong Wang, Tailin Chen, Xuming He, Yu Guan","submitted_at":"2021-08-10T09:25:07Z","abstract_excerpt":"The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion. Existing approaches typically employ a single neural representation for different motion patterns, which has difficulty in capturing fine-grained action classes given limited training data. To address the aforementioned problems, we propose a novel multi-granular spatio-temporal graph network for skeleton-based action classification that jointly models the coarse- and fine-grained skeleton motion patterns. To this end"},"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":"2108.04536","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-10T09:25:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8202fa8d9ebeeea1e2e550a26b4b8debec8bdc573ac13d373e4f0bf9f74e6463","abstract_canon_sha256":"0f5af299ce3851a198e3b7d7a28db612e2dd9b7b4c5ab0d348364c0c781cee40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:31.402224Z","signature_b64":"TWrfGjVARAQlBcmxBN2mktJm4fKzv3sJavwt8qKleYZcDQJTjH6cWmeuK3KARGPIoHBfheS0rf2R66LBlLUOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9a02aafec645448bdf457216ac827793657e788adda746581272cbed9e0b351","last_reissued_at":"2026-07-05T03:04:31.401819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:31.401819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Desen Zhou, Errui Ding, Jian Wang, Shidong Wang, Tailin Chen, Xuming He, Yu Guan","submitted_at":"2021-08-10T09:25:07Z","abstract_excerpt":"The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion. Existing approaches typically employ a single neural representation for different motion patterns, which has difficulty in capturing fine-grained action classes given limited training data. To address the aforementioned problems, we propose a novel multi-granular spatio-temporal graph network for skeleton-based action classification that jointly models the coarse- and fine-grained skeleton motion patterns. To this end"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04536","kind":"arxiv","version":1},"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/2108.04536/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":"2108.04536","created_at":"2026-07-05T03:04:31.401880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.04536v1","created_at":"2026-07-05T03:04:31.401880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04536","created_at":"2026-07-05T03:04:31.401880+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GQCVL7MMRKE","created_at":"2026-07-05T03:04:31.401880+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GQCVL7MMRKERPPU","created_at":"2026-07-05T03:04:31.401880+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GQCVL7M","created_at":"2026-07-05T03:04:31.401880+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/3GQCVL7MMRKERPPUK4QWVSBHPE","json":"https://pith.science/pith/3GQCVL7MMRKERPPUK4QWVSBHPE.json","graph_json":"https://pith.science/api/pith-number/3GQCVL7MMRKERPPUK4QWVSBHPE/graph.json","events_json":"https://pith.science/api/pith-number/3GQCVL7MMRKERPPUK4QWVSBHPE/events.json","paper":"https://pith.science/paper/3GQCVL7M"},"agent_actions":{"view_html":"https://pith.science/pith/3GQCVL7MMRKERPPUK4QWVSBHPE","download_json":"https://pith.science/pith/3GQCVL7MMRKERPPUK4QWVSBHPE.json","view_paper":"https://pith.science/paper/3GQCVL7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.04536&json=true","fetch_graph":"https://pith.science/api/pith-number/3GQCVL7MMRKERPPUK4QWVSBHPE/graph.json","fetch_events":"https://pith.science/api/pith-number/3GQCVL7MMRKERPPUK4QWVSBHPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GQCVL7MMRKERPPUK4QWVSBHPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GQCVL7MMRKERPPUK4QWVSBHPE/action/storage_attestation","attest_author":"https://pith.science/pith/3GQCVL7MMRKERPPUK4QWVSBHPE/action/author_attestation","sign_citation":"https://pith.science/pith/3GQCVL7MMRKERPPUK4QWVSBHPE/action/citation_signature","submit_replication":"https://pith.science/pith/3GQCVL7MMRKERPPUK4QWVSBHPE/action/replication_record"}},"created_at":"2026-07-05T03:04:31.401880+00:00","updated_at":"2026-07-05T03:04:31.401880+00:00"}