{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7DTSECAN72IZ47DVO3GVIXB4Y7","short_pith_number":"pith:7DTSECAN","schema_version":"1.0","canonical_sha256":"f8e722080dfe919e7c7576cd545c3cc7f2a00559d289043807fa689487256aeb","source":{"kind":"arxiv","id":"2107.12213","version":2},"attestation_state":"computed","paper":{"title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chunfeng Yuan, Weiming Hu, Ying Deng, Yuxin Chen, Ziqi Zhang","submitted_at":"2021-07-26T13:37:50Z","abstract_excerpt":"Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. In GCNs, graph topology dominates feature aggregation and therefore is the key to extracting representative features. In this work, we propose a novel Channel-wise Topology Refinement Graph Convolution (CTR-GC) to dynamically learn different topologies and effectively aggregate joint features in different channels for skeleton-based action recognition. The proposed CTR-GC models channel-wise topologies through learning a shared topology as a generic prior for all chan"},"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":"2107.12213","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-26T13:37:50Z","cross_cats_sorted":[],"title_canon_sha256":"bd2bbea752ee92b1457ea43bd775df90c33e27cf95466eb233cde6ea2d38fceb","abstract_canon_sha256":"072c41cf031445629f92c7cd583730b8f221d48bd44e8c69d7e5675ba938f33a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:50.756920Z","signature_b64":"ufRnZ1U1b6GkqaPB6dPPWlNI/y8bd9eCIM0eRURXV6iOGZODHRb15CLu/TEM9Bgm78UjTNG3Dl7NE+9s/V+eBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8e722080dfe919e7c7576cd545c3cc7f2a00559d289043807fa689487256aeb","last_reissued_at":"2026-07-05T03:07:50.756565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:50.756565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chunfeng Yuan, Weiming Hu, Ying Deng, Yuxin Chen, Ziqi Zhang","submitted_at":"2021-07-26T13:37:50Z","abstract_excerpt":"Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. In GCNs, graph topology dominates feature aggregation and therefore is the key to extracting representative features. In this work, we propose a novel Channel-wise Topology Refinement Graph Convolution (CTR-GC) to dynamically learn different topologies and effectively aggregate joint features in different channels for skeleton-based action recognition. The proposed CTR-GC models channel-wise topologies through learning a shared topology as a generic prior for all chan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12213","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/2107.12213/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":"2107.12213","created_at":"2026-07-05T03:07:50.756628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.12213v2","created_at":"2026-07-05T03:07:50.756628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12213","created_at":"2026-07-05T03:07:50.756628+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DTSECAN72IZ","created_at":"2026-07-05T03:07:50.756628+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DTSECAN72IZ47DV","created_at":"2026-07-05T03:07:50.756628+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DTSECAN","created_at":"2026-07-05T03:07:50.756628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00692","citing_title":"CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DTSECAN72IZ47DVO3GVIXB4Y7","json":"https://pith.science/pith/7DTSECAN72IZ47DVO3GVIXB4Y7.json","graph_json":"https://pith.science/api/pith-number/7DTSECAN72IZ47DVO3GVIXB4Y7/graph.json","events_json":"https://pith.science/api/pith-number/7DTSECAN72IZ47DVO3GVIXB4Y7/events.json","paper":"https://pith.science/paper/7DTSECAN"},"agent_actions":{"view_html":"https://pith.science/pith/7DTSECAN72IZ47DVO3GVIXB4Y7","download_json":"https://pith.science/pith/7DTSECAN72IZ47DVO3GVIXB4Y7.json","view_paper":"https://pith.science/paper/7DTSECAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.12213&json=true","fetch_graph":"https://pith.science/api/pith-number/7DTSECAN72IZ47DVO3GVIXB4Y7/graph.json","fetch_events":"https://pith.science/api/pith-number/7DTSECAN72IZ47DVO3GVIXB4Y7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DTSECAN72IZ47DVO3GVIXB4Y7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DTSECAN72IZ47DVO3GVIXB4Y7/action/storage_attestation","attest_author":"https://pith.science/pith/7DTSECAN72IZ47DVO3GVIXB4Y7/action/author_attestation","sign_citation":"https://pith.science/pith/7DTSECAN72IZ47DVO3GVIXB4Y7/action/citation_signature","submit_replication":"https://pith.science/pith/7DTSECAN72IZ47DVO3GVIXB4Y7/action/replication_record"}},"created_at":"2026-07-05T03:07:50.756628+00:00","updated_at":"2026-07-05T03:07:50.756628+00:00"}