{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FLK4E5LIIUCSEMO3RNIYTCX6GP","short_pith_number":"pith:FLK4E5LI","schema_version":"1.0","canonical_sha256":"2ad5c2756845052231db8b51898afe33cbca27add4f3a0b3bd703b2d2e723d75","source":{"kind":"arxiv","id":"1705.01861","version":3},"attestation_state":"computed","paper":{"title":"Action Tubelet Detector for Spatio-Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Philippe Weinzaepfel, Vicky Kalogeiton, Vittorio Ferrari","submitted_at":"2017-05-04T14:41:56Z","abstract_excerpt":"Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level that are then linked or tracked across time. In this paper, we leverage the temporal continuity of videos instead of operating at the frame level. We propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, i.e., sequences of bounding boxes with associated scores. The same way state-of-the-art object detectors rely on anchor boxes, our ACT-detector is based on anchor cuboids. We build upon the SSD framework. Convolutional fea"},"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":"1705.01861","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-04T14:41:56Z","cross_cats_sorted":[],"title_canon_sha256":"18bf533073418db95af4eba75c8621899478259a3471bc28c79b5a6ffb901059","abstract_canon_sha256":"8adc84f60efb7d22ef9d7a1ec4dd9436f910d88fd94e78908714b6c2fb5e506c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:47.454950Z","signature_b64":"oE2y3eJpRDFEZ5MhjG9tcNDeU8pDVWFcsvgOgxdVe0cyq71/dSgYtC+VVoJNIjpWU4XLk50HFHRkuDIJRoRtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ad5c2756845052231db8b51898afe33cbca27add4f3a0b3bd703b2d2e723d75","last_reissued_at":"2026-05-18T00:37:47.454210Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:47.454210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action Tubelet Detector for Spatio-Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Philippe Weinzaepfel, Vicky Kalogeiton, Vittorio Ferrari","submitted_at":"2017-05-04T14:41:56Z","abstract_excerpt":"Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level that are then linked or tracked across time. In this paper, we leverage the temporal continuity of videos instead of operating at the frame level. We propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, i.e., sequences of bounding boxes with associated scores. The same way state-of-the-art object detectors rely on anchor boxes, our ACT-detector is based on anchor cuboids. We build upon the SSD framework. Convolutional fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01861","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1705.01861","created_at":"2026-05-18T00:37:47.454333+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.01861v3","created_at":"2026-05-18T00:37:47.454333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01861","created_at":"2026-05-18T00:37:47.454333+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLK4E5LIIUCS","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLK4E5LIIUCSEMO3","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLK4E5LI","created_at":"2026-05-18T12:31:15.632608+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/FLK4E5LIIUCSEMO3RNIYTCX6GP","json":"https://pith.science/pith/FLK4E5LIIUCSEMO3RNIYTCX6GP.json","graph_json":"https://pith.science/api/pith-number/FLK4E5LIIUCSEMO3RNIYTCX6GP/graph.json","events_json":"https://pith.science/api/pith-number/FLK4E5LIIUCSEMO3RNIYTCX6GP/events.json","paper":"https://pith.science/paper/FLK4E5LI"},"agent_actions":{"view_html":"https://pith.science/pith/FLK4E5LIIUCSEMO3RNIYTCX6GP","download_json":"https://pith.science/pith/FLK4E5LIIUCSEMO3RNIYTCX6GP.json","view_paper":"https://pith.science/paper/FLK4E5LI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.01861&json=true","fetch_graph":"https://pith.science/api/pith-number/FLK4E5LIIUCSEMO3RNIYTCX6GP/graph.json","fetch_events":"https://pith.science/api/pith-number/FLK4E5LIIUCSEMO3RNIYTCX6GP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLK4E5LIIUCSEMO3RNIYTCX6GP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLK4E5LIIUCSEMO3RNIYTCX6GP/action/storage_attestation","attest_author":"https://pith.science/pith/FLK4E5LIIUCSEMO3RNIYTCX6GP/action/author_attestation","sign_citation":"https://pith.science/pith/FLK4E5LIIUCSEMO3RNIYTCX6GP/action/citation_signature","submit_replication":"https://pith.science/pith/FLK4E5LIIUCSEMO3RNIYTCX6GP/action/replication_record"}},"created_at":"2026-05-18T00:37:47.454333+00:00","updated_at":"2026-05-18T00:37:47.454333+00:00"}