{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DUFY6IUPHJCW3V5EEDH6QEB2KX","short_pith_number":"pith:DUFY6IUP","schema_version":"1.0","canonical_sha256":"1d0b8f228f3a456dd7a420cfe8103a55fdb13454924a9a9ea9ec019ffb923089","source":{"kind":"arxiv","id":"2211.09590","version":5},"attestation_state":"computed","paper":{"title":"Hypergraph Transformer for Skeleton-based Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Li, Margret Keuper, Xuansong Xie, Yanwen Fang, Yifeng Geng, Yuxuan Zhou, Zhi-Qi Cheng","submitted_at":"2022-11-17T15:36:48Z","abstract_excerpt":"Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections. By defining a graph with joints as vertices and their natural connections as edges, previous works successfully adopted Graph Convolutional networks (GCNs) to model joint co-occurrences and achieved superior performance. More recently, a limitation of GCNs is identified, i.e., the topology is fixed after training. To relax such a restriction, Self-Attention (SA) mechanism has been adopted to make the topology of GCNs adaptive to the input, resulting in the state-of-th"},"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":"2211.09590","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T15:36:48Z","cross_cats_sorted":[],"title_canon_sha256":"861ab20595ce534f34b53e168dd4e2d1b049938add4722935ce1f963834b95b2","abstract_canon_sha256":"83b4e52ef4f8ea2a457084b57e0b5ee90e0ce9830b293f4ae55bfce533427620"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:34.653972Z","signature_b64":"JOURdSmh7mUy/2MQmIESFvzVghEScoDRFn22+87w2Ht01ZWk6bE9q+mvrnH4n8TQdb4FIX/CQnJ3YBJ4d6EaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d0b8f228f3a456dd7a420cfe8103a55fdb13454924a9a9ea9ec019ffb923089","last_reissued_at":"2026-07-05T05:53:34.653554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:34.653554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hypergraph Transformer for Skeleton-based Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Li, Margret Keuper, Xuansong Xie, Yanwen Fang, Yifeng Geng, Yuxuan Zhou, Zhi-Qi Cheng","submitted_at":"2022-11-17T15:36:48Z","abstract_excerpt":"Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections. By defining a graph with joints as vertices and their natural connections as edges, previous works successfully adopted Graph Convolutional networks (GCNs) to model joint co-occurrences and achieved superior performance. More recently, a limitation of GCNs is identified, i.e., the topology is fixed after training. To relax such a restriction, Self-Attention (SA) mechanism has been adopted to make the topology of GCNs adaptive to the input, resulting in the state-of-th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09590","kind":"arxiv","version":5},"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/2211.09590/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":"2211.09590","created_at":"2026-07-05T05:53:34.653612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09590v5","created_at":"2026-07-05T05:53:34.653612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09590","created_at":"2026-07-05T05:53:34.653612+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUFY6IUPHJCW","created_at":"2026-07-05T05:53:34.653612+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUFY6IUPHJCW3V5E","created_at":"2026-07-05T05:53:34.653612+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUFY6IUP","created_at":"2026-07-05T05:53:34.653612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00716","citing_title":"Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09523","citing_title":"Patch-Wise Hypergraph Contrastive Learning with Dual Normal Distribution Weighting for Multi-Domain Stain Transfer","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUFY6IUPHJCW3V5EEDH6QEB2KX","json":"https://pith.science/pith/DUFY6IUPHJCW3V5EEDH6QEB2KX.json","graph_json":"https://pith.science/api/pith-number/DUFY6IUPHJCW3V5EEDH6QEB2KX/graph.json","events_json":"https://pith.science/api/pith-number/DUFY6IUPHJCW3V5EEDH6QEB2KX/events.json","paper":"https://pith.science/paper/DUFY6IUP"},"agent_actions":{"view_html":"https://pith.science/pith/DUFY6IUPHJCW3V5EEDH6QEB2KX","download_json":"https://pith.science/pith/DUFY6IUPHJCW3V5EEDH6QEB2KX.json","view_paper":"https://pith.science/paper/DUFY6IUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09590&json=true","fetch_graph":"https://pith.science/api/pith-number/DUFY6IUPHJCW3V5EEDH6QEB2KX/graph.json","fetch_events":"https://pith.science/api/pith-number/DUFY6IUPHJCW3V5EEDH6QEB2KX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUFY6IUPHJCW3V5EEDH6QEB2KX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUFY6IUPHJCW3V5EEDH6QEB2KX/action/storage_attestation","attest_author":"https://pith.science/pith/DUFY6IUPHJCW3V5EEDH6QEB2KX/action/author_attestation","sign_citation":"https://pith.science/pith/DUFY6IUPHJCW3V5EEDH6QEB2KX/action/citation_signature","submit_replication":"https://pith.science/pith/DUFY6IUPHJCW3V5EEDH6QEB2KX/action/replication_record"}},"created_at":"2026-07-05T05:53:34.653612+00:00","updated_at":"2026-07-05T05:53:34.653612+00:00"}