{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:R3273EKDWWNI72PEIXLN2A3Z6W","short_pith_number":"pith:R3273EKD","schema_version":"1.0","canonical_sha256":"8ef5fd9143b59a8fe9e445d6dd0379f5a425dad2c9a8f7c40f34b201e7fda01b","source":{"kind":"arxiv","id":"1911.06644","version":5},"attestation_state":"computed","paper":{"title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gerhard Rigoll, Okan K\\\"op\\\"ukl\\\"u, Xiangyu Wei","submitted_at":"2019-11-15T14:09:47Z","abstract_excerpt":"Spatiotemporal action localization requires the incorporation of two sources of information into the designed architecture: (1) temporal information from the previous frames and (2) spatial information from the key frame. Current state-of-the-art approaches usually extract these information with separate networks and use an extra mechanism for fusion to get detections. In this work, we present YOWO, a unified CNN architecture for real-time spatiotemporal action localization in video streams. YOWO is a single-stage architecture with two branches to extract temporal and spatial information concu"},"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":"1911.06644","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-15T14:09:47Z","cross_cats_sorted":[],"title_canon_sha256":"1bee6cbe1dbcadaee27db1e7ef8987c1658453209bd2ed8887f8a1900c4e992c","abstract_canon_sha256":"856f4148125a4613a37de3324d54535bcab68b9f90439a9645f0e996bebdcf5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:03.872725Z","signature_b64":"4xYGEJspX4yEz7ZD4GDlTfKn+NSGMzrpFlIswcrWw+6KjK5QcKXU/UUY2xA1E+dLB4YfGUILH/G+6gjaPuPKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ef5fd9143b59a8fe9e445d6dd0379f5a425dad2c9a8f7c40f34b201e7fda01b","last_reissued_at":"2026-07-05T03:23:03.872327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:03.872327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gerhard Rigoll, Okan K\\\"op\\\"ukl\\\"u, Xiangyu Wei","submitted_at":"2019-11-15T14:09:47Z","abstract_excerpt":"Spatiotemporal action localization requires the incorporation of two sources of information into the designed architecture: (1) temporal information from the previous frames and (2) spatial information from the key frame. Current state-of-the-art approaches usually extract these information with separate networks and use an extra mechanism for fusion to get detections. In this work, we present YOWO, a unified CNN architecture for real-time spatiotemporal action localization in video streams. YOWO is a single-stage architecture with two branches to extract temporal and spatial information concu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06644","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/1911.06644/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":"1911.06644","created_at":"2026-07-05T03:23:03.872385+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.06644v5","created_at":"2026-07-05T03:23:03.872385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06644","created_at":"2026-07-05T03:23:03.872385+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3273EKDWWNI","created_at":"2026-07-05T03:23:03.872385+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3273EKDWWNI72PE","created_at":"2026-07-05T03:23:03.872385+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3273EKD","created_at":"2026-07-05T03:23:03.872385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31421","citing_title":"Temporal Preservation over Processing: Diagnosing and Designing Spatiotemporal Single-Stage Video Detectors","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04750","citing_title":"VC-FeS: Viewpoint-Conditioned Feature Selection for Vehicle Re-identification in Thermal Vision","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3273EKDWWNI72PEIXLN2A3Z6W","json":"https://pith.science/pith/R3273EKDWWNI72PEIXLN2A3Z6W.json","graph_json":"https://pith.science/api/pith-number/R3273EKDWWNI72PEIXLN2A3Z6W/graph.json","events_json":"https://pith.science/api/pith-number/R3273EKDWWNI72PEIXLN2A3Z6W/events.json","paper":"https://pith.science/paper/R3273EKD"},"agent_actions":{"view_html":"https://pith.science/pith/R3273EKDWWNI72PEIXLN2A3Z6W","download_json":"https://pith.science/pith/R3273EKDWWNI72PEIXLN2A3Z6W.json","view_paper":"https://pith.science/paper/R3273EKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.06644&json=true","fetch_graph":"https://pith.science/api/pith-number/R3273EKDWWNI72PEIXLN2A3Z6W/graph.json","fetch_events":"https://pith.science/api/pith-number/R3273EKDWWNI72PEIXLN2A3Z6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3273EKDWWNI72PEIXLN2A3Z6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3273EKDWWNI72PEIXLN2A3Z6W/action/storage_attestation","attest_author":"https://pith.science/pith/R3273EKDWWNI72PEIXLN2A3Z6W/action/author_attestation","sign_citation":"https://pith.science/pith/R3273EKDWWNI72PEIXLN2A3Z6W/action/citation_signature","submit_replication":"https://pith.science/pith/R3273EKDWWNI72PEIXLN2A3Z6W/action/replication_record"}},"created_at":"2026-07-05T03:23:03.872385+00:00","updated_at":"2026-07-05T03:23:03.872385+00:00"}