{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WCVMLZUJGOQTQ6B2JJSQXCN3MD","short_pith_number":"pith:WCVMLZUJ","schema_version":"1.0","canonical_sha256":"b0aac5e68933a138783a4a650b89bb60d38702e82512ea06dd4b17bcf56b7a3a","source":{"kind":"arxiv","id":"2403.15212","version":3},"attestation_state":"computed","paper":{"title":"GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Ni, Lei Jiang, Weixin Yang, Xin Zhang","submitted_at":"2024-03-22T13:55:52Z","abstract_excerpt":"Skeleton-based action recognition (SAR) in videos is an important but challenging task in computer vision. The recent state-of-the-art (SOTA) models for SAR are primarily based on graph convolutional neural networks (GCNs), which are powerful in extracting the spatial information from skeleton data. However, their ability to capture temporal dynamics remains limited. To address this, we propose the G-Dev layer, which leverages path development-a principled and parsimonious representation for sequential data based on Lie group structures-to enhance temporal modeling. By integrating the G-Dev la"},"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":"2403.15212","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T13:55:52Z","cross_cats_sorted":[],"title_canon_sha256":"80b545fc69b3f56d5fdbcca64b20c813816ec528a9ac59640aa7ba8707b32ef7","abstract_canon_sha256":"ed863276719378969ccb9fa1ae59ed61d41b5a639be883850a952a629eb442f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:16:47.818992Z","signature_b64":"OFGSlad42HhtR90uxarFbt0TJDvS8+VQ2h4Y+y4QvIWCYccIG2jj6pbzw8dOt+Vr5rNL7KaeRWcU1GN85HS9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0aac5e68933a138783a4a650b89bb60d38702e82512ea06dd4b17bcf56b7a3a","last_reissued_at":"2026-06-30T02:16:47.818422Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:16:47.818422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Ni, Lei Jiang, Weixin Yang, Xin Zhang","submitted_at":"2024-03-22T13:55:52Z","abstract_excerpt":"Skeleton-based action recognition (SAR) in videos is an important but challenging task in computer vision. The recent state-of-the-art (SOTA) models for SAR are primarily based on graph convolutional neural networks (GCNs), which are powerful in extracting the spatial information from skeleton data. However, their ability to capture temporal dynamics remains limited. To address this, we propose the G-Dev layer, which leverages path development-a principled and parsimonious representation for sequential data based on Lie group structures-to enhance temporal modeling. By integrating the G-Dev la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15212","kind":"arxiv","version":3},"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/2403.15212/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":"2403.15212","created_at":"2026-06-30T02:16:47.818497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15212v3","created_at":"2026-06-30T02:16:47.818497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15212","created_at":"2026-06-30T02:16:47.818497+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCVMLZUJGOQT","created_at":"2026-06-30T02:16:47.818497+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCVMLZUJGOQTQ6B2","created_at":"2026-06-30T02:16:47.818497+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCVMLZUJ","created_at":"2026-06-30T02:16:47.818497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18048","citing_title":"SHARDeg: A Benchmark for Skeletal Human Action Recognition in Degraded Scenarios","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCVMLZUJGOQTQ6B2JJSQXCN3MD","json":"https://pith.science/pith/WCVMLZUJGOQTQ6B2JJSQXCN3MD.json","graph_json":"https://pith.science/api/pith-number/WCVMLZUJGOQTQ6B2JJSQXCN3MD/graph.json","events_json":"https://pith.science/api/pith-number/WCVMLZUJGOQTQ6B2JJSQXCN3MD/events.json","paper":"https://pith.science/paper/WCVMLZUJ"},"agent_actions":{"view_html":"https://pith.science/pith/WCVMLZUJGOQTQ6B2JJSQXCN3MD","download_json":"https://pith.science/pith/WCVMLZUJGOQTQ6B2JJSQXCN3MD.json","view_paper":"https://pith.science/paper/WCVMLZUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15212&json=true","fetch_graph":"https://pith.science/api/pith-number/WCVMLZUJGOQTQ6B2JJSQXCN3MD/graph.json","fetch_events":"https://pith.science/api/pith-number/WCVMLZUJGOQTQ6B2JJSQXCN3MD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCVMLZUJGOQTQ6B2JJSQXCN3MD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCVMLZUJGOQTQ6B2JJSQXCN3MD/action/storage_attestation","attest_author":"https://pith.science/pith/WCVMLZUJGOQTQ6B2JJSQXCN3MD/action/author_attestation","sign_citation":"https://pith.science/pith/WCVMLZUJGOQTQ6B2JJSQXCN3MD/action/citation_signature","submit_replication":"https://pith.science/pith/WCVMLZUJGOQTQ6B2JJSQXCN3MD/action/replication_record"}},"created_at":"2026-06-30T02:16:47.818497+00:00","updated_at":"2026-06-30T02:16:47.818497+00:00"}