{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7ZMBEGO23Z24FVJ3ELSP53T33L","short_pith_number":"pith:7ZMBEGO2","schema_version":"1.0","canonical_sha256":"fe581219dade75c2d53b22e4feee7bdae176144ad80daa1dd36d56eb6d6f960f","source":{"kind":"arxiv","id":"2203.10584","version":1},"attestation_state":"computed","paper":{"title":"Point3D: tracking actions as moving points with 3D CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bhiksha Raj, Jingfei Xia, Shentong Mo, Xiaoqing Tan","submitted_at":"2022-03-20T15:41:47Z","abstract_excerpt":"Spatio-temporal action recognition has been a challenging task that involves detecting where and when actions occur. Current state-of-the-art action detectors are mostly anchor-based, requiring sensitive anchor designs and huge computations due to calculating large numbers of anchor boxes. Motivated by nascent anchor-free approaches, we propose Point3D, a flexible and computationally efficient network with high precision for spatio-temporal action recognition. Our Point3D consists of a Point Head for action localization and a 3D Head for action classification. Firstly, Point Head is used to tr"},"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":"2203.10584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-20T15:41:47Z","cross_cats_sorted":[],"title_canon_sha256":"6e5796387868c2675a8a686ccd3cd968c3494d6b3c864827ab81e7a48a1079ec","abstract_canon_sha256":"681f422aa2ae6b551686159c5462b1d90f2e92f58270fbc14b44590208989bb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:54.676118Z","signature_b64":"hxWE7aW5IV0OlBueRR6MejEsgS5Xo1MJe0YVGq2BXzi1a5R9FUoBc7ZPC7Haxd1a2AsJnAMUFOxoQFxlx0dHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe581219dade75c2d53b22e4feee7bdae176144ad80daa1dd36d56eb6d6f960f","last_reissued_at":"2026-07-05T04:06:54.675683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:54.675683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Point3D: tracking actions as moving points with 3D CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bhiksha Raj, Jingfei Xia, Shentong Mo, Xiaoqing Tan","submitted_at":"2022-03-20T15:41:47Z","abstract_excerpt":"Spatio-temporal action recognition has been a challenging task that involves detecting where and when actions occur. Current state-of-the-art action detectors are mostly anchor-based, requiring sensitive anchor designs and huge computations due to calculating large numbers of anchor boxes. Motivated by nascent anchor-free approaches, we propose Point3D, a flexible and computationally efficient network with high precision for spatio-temporal action recognition. Our Point3D consists of a Point Head for action localization and a 3D Head for action classification. Firstly, Point Head is used to tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10584","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/2203.10584/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":"2203.10584","created_at":"2026-07-05T04:06:54.675751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10584v1","created_at":"2026-07-05T04:06:54.675751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10584","created_at":"2026-07-05T04:06:54.675751+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZMBEGO23Z24","created_at":"2026-07-05T04:06:54.675751+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZMBEGO23Z24FVJ3","created_at":"2026-07-05T04:06:54.675751+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZMBEGO2","created_at":"2026-07-05T04:06:54.675751+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/7ZMBEGO23Z24FVJ3ELSP53T33L","json":"https://pith.science/pith/7ZMBEGO23Z24FVJ3ELSP53T33L.json","graph_json":"https://pith.science/api/pith-number/7ZMBEGO23Z24FVJ3ELSP53T33L/graph.json","events_json":"https://pith.science/api/pith-number/7ZMBEGO23Z24FVJ3ELSP53T33L/events.json","paper":"https://pith.science/paper/7ZMBEGO2"},"agent_actions":{"view_html":"https://pith.science/pith/7ZMBEGO23Z24FVJ3ELSP53T33L","download_json":"https://pith.science/pith/7ZMBEGO23Z24FVJ3ELSP53T33L.json","view_paper":"https://pith.science/paper/7ZMBEGO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10584&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZMBEGO23Z24FVJ3ELSP53T33L/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZMBEGO23Z24FVJ3ELSP53T33L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZMBEGO23Z24FVJ3ELSP53T33L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZMBEGO23Z24FVJ3ELSP53T33L/action/storage_attestation","attest_author":"https://pith.science/pith/7ZMBEGO23Z24FVJ3ELSP53T33L/action/author_attestation","sign_citation":"https://pith.science/pith/7ZMBEGO23Z24FVJ3ELSP53T33L/action/citation_signature","submit_replication":"https://pith.science/pith/7ZMBEGO23Z24FVJ3ELSP53T33L/action/replication_record"}},"created_at":"2026-07-05T04:06:54.675751+00:00","updated_at":"2026-07-05T04:06:54.675751+00:00"}