{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IQQOOLWLTL77PPUQ3T2WWC7EAO","short_pith_number":"pith:IQQOOLWL","schema_version":"1.0","canonical_sha256":"4420e72ecb9afff7be90dcf56b0be403bb348ac6468f1359b285defe0844e843","source":{"kind":"arxiv","id":"2210.07503","version":1},"attestation_state":"computed","paper":{"title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Byoung Chul Ko, Dasom Ahn, Hyunsu Hong, Sangwon Kim","submitted_at":"2022-10-14T04:09:44Z","abstract_excerpt":"In action recognition, although the combination of spatio-temporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature representation for cross-modal data are required. To solve these problems, we propose Spatio-TemporAl cRoss (STAR)-transformer, which can effectively represent two cross-modal features as a recognizable vector. First, from the input video and skeleton sequence, video frames are output as global grid tokens and skeletons are output as joint map tokens, respectively. These tokens are then aggregated into multi-class tokens"},"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":"2210.07503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-14T04:09:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d2e9a5381616f9ad84c48fcb58fae93d46d532eb66d12b4a9afc9ee1733dbbb","abstract_canon_sha256":"f423325550fe1badfd4d2d9b9360afe03c08bc9e50d0bc0dd216790421fb117e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:37.976478Z","signature_b64":"wUD3pgDJe3G0DkootLkxq0h1hOUXG/tk/wVPl8FgOP4qMLQX7mO5iS+v/vz349gpMVtDbji1A3AxmpQGKsp+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4420e72ecb9afff7be90dcf56b0be403bb348ac6468f1359b285defe0844e843","last_reissued_at":"2026-07-05T05:06:37.976059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:37.976059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Byoung Chul Ko, Dasom Ahn, Hyunsu Hong, Sangwon Kim","submitted_at":"2022-10-14T04:09:44Z","abstract_excerpt":"In action recognition, although the combination of spatio-temporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature representation for cross-modal data are required. To solve these problems, we propose Spatio-TemporAl cRoss (STAR)-transformer, which can effectively represent two cross-modal features as a recognizable vector. First, from the input video and skeleton sequence, video frames are output as global grid tokens and skeletons are output as joint map tokens, respectively. These tokens are then aggregated into multi-class tokens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07503","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/2210.07503/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":"2210.07503","created_at":"2026-07-05T05:06:37.976117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07503v1","created_at":"2026-07-05T05:06:37.976117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07503","created_at":"2026-07-05T05:06:37.976117+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQQOOLWLTL77","created_at":"2026-07-05T05:06:37.976117+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQQOOLWLTL77PPUQ","created_at":"2026-07-05T05:06:37.976117+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQQOOLWL","created_at":"2026-07-05T05:06:37.976117+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/IQQOOLWLTL77PPUQ3T2WWC7EAO","json":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO.json","graph_json":"https://pith.science/api/pith-number/IQQOOLWLTL77PPUQ3T2WWC7EAO/graph.json","events_json":"https://pith.science/api/pith-number/IQQOOLWLTL77PPUQ3T2WWC7EAO/events.json","paper":"https://pith.science/paper/IQQOOLWL"},"agent_actions":{"view_html":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO","download_json":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO.json","view_paper":"https://pith.science/paper/IQQOOLWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07503&json=true","fetch_graph":"https://pith.science/api/pith-number/IQQOOLWLTL77PPUQ3T2WWC7EAO/graph.json","fetch_events":"https://pith.science/api/pith-number/IQQOOLWLTL77PPUQ3T2WWC7EAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO/action/storage_attestation","attest_author":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO/action/author_attestation","sign_citation":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO/action/citation_signature","submit_replication":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO/action/replication_record"}},"created_at":"2026-07-05T05:06:37.976117+00:00","updated_at":"2026-07-05T05:06:37.976117+00:00"}