{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UONLJOYLKWY4LEAUURR42HZXNB","short_pith_number":"pith:UONLJOYL","schema_version":"1.0","canonical_sha256":"a39ab4bb0b55b1c59014a463cd1f376869c6449345bb889f966d5807245f42c3","source":{"kind":"arxiv","id":"2304.00254","version":2},"attestation_state":"computed","paper":{"title":"DOAD: Decoupled One Stage Action Detection Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Wang, Jiashi Feng, Mike Zheng Show, Pichao Wang, Shuning Chang","submitted_at":"2023-04-01T08:06:43Z","abstract_excerpt":"Localizing people and recognizing their actions from videos is a challenging task towards high-level video understanding. Existing methods are mostly two-stage based, with one stage for person bounding box generation and the other stage for action recognition. However, such two-stage methods are generally with low efficiency. We observe that directly unifying detection and action recognition normally suffers from (i) inferior learning due to different desired properties of context representation for detection and action recognition; (ii) optimization difficulty with insufficient training data."},"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":"2304.00254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-01T08:06:43Z","cross_cats_sorted":[],"title_canon_sha256":"79625730225903068b41fb8fcc6443f55a59bec9d4ef6af1af53e5ed652fa744","abstract_canon_sha256":"595bbb007f23eea6d853ffa221c1424fddb447bf041d47742a7e736fb01f39ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:37.181692Z","signature_b64":"f6AxDski66oR+zgdS6yZV8f1N9pha4orYnO3WGaJImfawtIxe/S9ifJpZ4dWeu67pARVV160hiS0EjyJzrQsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a39ab4bb0b55b1c59014a463cd1f376869c6449345bb889f966d5807245f42c3","last_reissued_at":"2026-07-05T05:57:37.181234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:37.181234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DOAD: Decoupled One Stage Action Detection Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Wang, Jiashi Feng, Mike Zheng Show, Pichao Wang, Shuning Chang","submitted_at":"2023-04-01T08:06:43Z","abstract_excerpt":"Localizing people and recognizing their actions from videos is a challenging task towards high-level video understanding. Existing methods are mostly two-stage based, with one stage for person bounding box generation and the other stage for action recognition. However, such two-stage methods are generally with low efficiency. We observe that directly unifying detection and action recognition normally suffers from (i) inferior learning due to different desired properties of context representation for detection and action recognition; (ii) optimization difficulty with insufficient training data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00254","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/2304.00254/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":"2304.00254","created_at":"2026-07-05T05:57:37.181289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00254v2","created_at":"2026-07-05T05:57:37.181289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00254","created_at":"2026-07-05T05:57:37.181289+00:00"},{"alias_kind":"pith_short_12","alias_value":"UONLJOYLKWY4","created_at":"2026-07-05T05:57:37.181289+00:00"},{"alias_kind":"pith_short_16","alias_value":"UONLJOYLKWY4LEAU","created_at":"2026-07-05T05:57:37.181289+00:00"},{"alias_kind":"pith_short_8","alias_value":"UONLJOYL","created_at":"2026-07-05T05:57:37.181289+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/UONLJOYLKWY4LEAUURR42HZXNB","json":"https://pith.science/pith/UONLJOYLKWY4LEAUURR42HZXNB.json","graph_json":"https://pith.science/api/pith-number/UONLJOYLKWY4LEAUURR42HZXNB/graph.json","events_json":"https://pith.science/api/pith-number/UONLJOYLKWY4LEAUURR42HZXNB/events.json","paper":"https://pith.science/paper/UONLJOYL"},"agent_actions":{"view_html":"https://pith.science/pith/UONLJOYLKWY4LEAUURR42HZXNB","download_json":"https://pith.science/pith/UONLJOYLKWY4LEAUURR42HZXNB.json","view_paper":"https://pith.science/paper/UONLJOYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00254&json=true","fetch_graph":"https://pith.science/api/pith-number/UONLJOYLKWY4LEAUURR42HZXNB/graph.json","fetch_events":"https://pith.science/api/pith-number/UONLJOYLKWY4LEAUURR42HZXNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UONLJOYLKWY4LEAUURR42HZXNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UONLJOYLKWY4LEAUURR42HZXNB/action/storage_attestation","attest_author":"https://pith.science/pith/UONLJOYLKWY4LEAUURR42HZXNB/action/author_attestation","sign_citation":"https://pith.science/pith/UONLJOYLKWY4LEAUURR42HZXNB/action/citation_signature","submit_replication":"https://pith.science/pith/UONLJOYLKWY4LEAUURR42HZXNB/action/replication_record"}},"created_at":"2026-07-05T05:57:37.181289+00:00","updated_at":"2026-07-05T05:57:37.181289+00:00"}