{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Q4M7PS5RH55NFYQDOGPQXBPBXR","short_pith_number":"pith:Q4M7PS5R","schema_version":"1.0","canonical_sha256":"8719f7cbb13f7ad2e203719f0b85e1bc4c7800511c826397bed60784593241ec","source":{"kind":"arxiv","id":"1811.08496","version":2},"attestation_state":"computed","paper":{"title":"A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carlos D. Castillo, Joshua Gleason, Jun-Chen Cheng, Rajeev Ranjan, Rama Chellappa, Steven Schwarcz","submitted_at":"2018-11-20T21:35:07Z","abstract_excerpt":"Existing approaches for spatio-temporal action detection in videos are limited by the spatial extent and temporal duration of the actions. In this paper, we present a modular system for spatio-temporal action detection in untrimmed security videos. We propose a two stage approach. The first stage generates dense spatio-temporal proposals using hierarchical clustering and temporal jittering techniques on frame-wise object detections. The second stage is a Temporal Refinement I3D (TRI-3D) network that performs action classification and temporal refinement on the generated proposals. The object d"},"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":"1811.08496","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-20T21:35:07Z","cross_cats_sorted":[],"title_canon_sha256":"fd716e78a3324a1028d223312356f18b9fa3270f2c48ecb03d87500267eec4cc","abstract_canon_sha256":"800f4d61f3d43fbb444eea49c0c3a2e30f896d84564f453722dbdc24481c45b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:07.668840Z","signature_b64":"Tz/QKu2xWscSO8ZzZGqsF8aFZZCf8Hnk0+2PSEGSxvZSxXSnbDX1CQAnDVWHUa/tTFdVcwtYTHlom//Oh69HBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8719f7cbb13f7ad2e203719f0b85e1bc4c7800511c826397bed60784593241ec","last_reissued_at":"2026-05-18T00:00:07.668213Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:07.668213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carlos D. Castillo, Joshua Gleason, Jun-Chen Cheng, Rajeev Ranjan, Rama Chellappa, Steven Schwarcz","submitted_at":"2018-11-20T21:35:07Z","abstract_excerpt":"Existing approaches for spatio-temporal action detection in videos are limited by the spatial extent and temporal duration of the actions. In this paper, we present a modular system for spatio-temporal action detection in untrimmed security videos. We propose a two stage approach. The first stage generates dense spatio-temporal proposals using hierarchical clustering and temporal jittering techniques on frame-wise object detections. The second stage is a Temporal Refinement I3D (TRI-3D) network that performs action classification and temporal refinement on the generated proposals. The object d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08496","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":""},"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":"1811.08496","created_at":"2026-05-18T00:00:07.668310+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.08496v2","created_at":"2026-05-18T00:00:07.668310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08496","created_at":"2026-05-18T00:00:07.668310+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4M7PS5RH55N","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4M7PS5RH55NFYQD","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4M7PS5R","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.10899","citing_title":"Out the Window: A Crowd-Sourced Dataset for Activity Classification in Security Video","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q4M7PS5RH55NFYQDOGPQXBPBXR","json":"https://pith.science/pith/Q4M7PS5RH55NFYQDOGPQXBPBXR.json","graph_json":"https://pith.science/api/pith-number/Q4M7PS5RH55NFYQDOGPQXBPBXR/graph.json","events_json":"https://pith.science/api/pith-number/Q4M7PS5RH55NFYQDOGPQXBPBXR/events.json","paper":"https://pith.science/paper/Q4M7PS5R"},"agent_actions":{"view_html":"https://pith.science/pith/Q4M7PS5RH55NFYQDOGPQXBPBXR","download_json":"https://pith.science/pith/Q4M7PS5RH55NFYQDOGPQXBPBXR.json","view_paper":"https://pith.science/paper/Q4M7PS5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.08496&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4M7PS5RH55NFYQDOGPQXBPBXR/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4M7PS5RH55NFYQDOGPQXBPBXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4M7PS5RH55NFYQDOGPQXBPBXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4M7PS5RH55NFYQDOGPQXBPBXR/action/storage_attestation","attest_author":"https://pith.science/pith/Q4M7PS5RH55NFYQDOGPQXBPBXR/action/author_attestation","sign_citation":"https://pith.science/pith/Q4M7PS5RH55NFYQDOGPQXBPBXR/action/citation_signature","submit_replication":"https://pith.science/pith/Q4M7PS5RH55NFYQDOGPQXBPBXR/action/replication_record"}},"created_at":"2026-05-18T00:00:07.668310+00:00","updated_at":"2026-05-18T00:00:07.668310+00:00"}