{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VP26C33UHCIRJPPRTYFDGH3QN5","short_pith_number":"pith:VP26C33U","schema_version":"1.0","canonical_sha256":"abf5e16f74389114bdf19e0a331f706f6ef5c1e2c585c1facbc7b1cd33b319f1","source":{"kind":"arxiv","id":"2302.06848","version":2},"attestation_state":"computed","paper":{"title":"YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianhua Yang, Kun Dai","submitted_at":"2023-02-14T05:52:45Z","abstract_excerpt":"Designing a real-time framework for the spatio-temporal action detection task is still a challenge. In this paper, we propose a novel real-time action detection framework, YOWOv2. In this new framework, YOWOv2 takes advantage of both the 3D backbone and 2D backbone for accurate action detection. A multi-level detection pipeline is designed to detect action instances of different scales. To achieve this goal, we carefully build a simple and efficient 2D backbone with a feature pyramid network to extract different levels of classification features and regression features. For the 3D backbone, we"},"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":"2302.06848","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-14T05:52:45Z","cross_cats_sorted":[],"title_canon_sha256":"99195a55edee9f97700d3460445f190eb0e27928976f442bc84e0918d4cad107","abstract_canon_sha256":"5dfa31d5ad1b00eff019a0cc7ea3a00a0c72f13283108de51593a787a83edb49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:37.926871Z","signature_b64":"8LCYoi+qbHWXAAwEfh07rpioLq9tVIYWhZD8RjJnXGuqkhLm+Npzh8JlfJOqjCkNwSQgcz8Fp1MYRnTUCBHJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abf5e16f74389114bdf19e0a331f706f6ef5c1e2c585c1facbc7b1cd33b319f1","last_reissued_at":"2026-07-05T06:18:37.926343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:37.926343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianhua Yang, Kun Dai","submitted_at":"2023-02-14T05:52:45Z","abstract_excerpt":"Designing a real-time framework for the spatio-temporal action detection task is still a challenge. In this paper, we propose a novel real-time action detection framework, YOWOv2. In this new framework, YOWOv2 takes advantage of both the 3D backbone and 2D backbone for accurate action detection. A multi-level detection pipeline is designed to detect action instances of different scales. To achieve this goal, we carefully build a simple and efficient 2D backbone with a feature pyramid network to extract different levels of classification features and regression features. For the 3D backbone, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06848","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/2302.06848/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":"2302.06848","created_at":"2026-07-05T06:18:37.926425+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06848v2","created_at":"2026-07-05T06:18:37.926425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06848","created_at":"2026-07-05T06:18:37.926425+00:00"},{"alias_kind":"pith_short_12","alias_value":"VP26C33UHCIR","created_at":"2026-07-05T06:18:37.926425+00:00"},{"alias_kind":"pith_short_16","alias_value":"VP26C33UHCIRJPPR","created_at":"2026-07-05T06:18:37.926425+00:00"},{"alias_kind":"pith_short_8","alias_value":"VP26C33U","created_at":"2026-07-05T06:18:37.926425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07072","citing_title":"Stable Mean Teacher for Semi-supervised Video Action Detection","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VP26C33UHCIRJPPRTYFDGH3QN5","json":"https://pith.science/pith/VP26C33UHCIRJPPRTYFDGH3QN5.json","graph_json":"https://pith.science/api/pith-number/VP26C33UHCIRJPPRTYFDGH3QN5/graph.json","events_json":"https://pith.science/api/pith-number/VP26C33UHCIRJPPRTYFDGH3QN5/events.json","paper":"https://pith.science/paper/VP26C33U"},"agent_actions":{"view_html":"https://pith.science/pith/VP26C33UHCIRJPPRTYFDGH3QN5","download_json":"https://pith.science/pith/VP26C33UHCIRJPPRTYFDGH3QN5.json","view_paper":"https://pith.science/paper/VP26C33U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06848&json=true","fetch_graph":"https://pith.science/api/pith-number/VP26C33UHCIRJPPRTYFDGH3QN5/graph.json","fetch_events":"https://pith.science/api/pith-number/VP26C33UHCIRJPPRTYFDGH3QN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VP26C33UHCIRJPPRTYFDGH3QN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VP26C33UHCIRJPPRTYFDGH3QN5/action/storage_attestation","attest_author":"https://pith.science/pith/VP26C33UHCIRJPPRTYFDGH3QN5/action/author_attestation","sign_citation":"https://pith.science/pith/VP26C33UHCIRJPPRTYFDGH3QN5/action/citation_signature","submit_replication":"https://pith.science/pith/VP26C33UHCIRJPPRTYFDGH3QN5/action/replication_record"}},"created_at":"2026-07-05T06:18:37.926425+00:00","updated_at":"2026-07-05T06:18:37.926425+00:00"}