{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TU5RL2E4F6E4WKNDMPKCXW33M2","short_pith_number":"pith:TU5RL2E4","schema_version":"1.0","canonical_sha256":"9d3b15e89c2f89cb29a363d42bdb7b669680021698e74a5e9292c5a1317d193f","source":{"kind":"arxiv","id":"1812.03982","version":3},"attestation_state":"computed","paper":{"title":"SlowFast Networks for Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming He","submitted_at":"2018-12-10T18:59:07Z","abstract_excerpt":"We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution. The Fast pathway can be made very lightweight by reducing its channel capacity, yet can learn useful temporal information for video recognition. Our models achieve strong performance for both action classification and detection in video, and large improvements are pin-pointed as contributions by our SlowFast concept. We report state-of-the-art ac"},"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":"1812.03982","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-10T18:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"73dd1a90ed0acf6fc1fc8d35de079359120599df0d11696e255302b8ce3adfc2","abstract_canon_sha256":"ec026d29bfdcf0fbd4aecb9f55db57ed7e79b9fc0fb501d609cd320558f6827c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:22.395635Z","signature_b64":"nBVvB5TXVth7H2uqWZgb3OmhD3fNxgF4W333/wKx2P5Sf+FVMNyqYC46JBa4kGgBNF7Ig2aMlc0iwfy2d9HCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d3b15e89c2f89cb29a363d42bdb7b669680021698e74a5e9292c5a1317d193f","last_reissued_at":"2026-07-05T00:15:22.395138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:22.395138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SlowFast Networks for Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming He","submitted_at":"2018-12-10T18:59:07Z","abstract_excerpt":"We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution. The Fast pathway can be made very lightweight by reducing its channel capacity, yet can learn useful temporal information for video recognition. Our models achieve strong performance for both action classification and detection in video, and large improvements are pin-pointed as contributions by our SlowFast concept. We report state-of-the-art ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03982","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1812.03982/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":"1812.03982","created_at":"2026-07-05T00:15:22.395193+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.03982v3","created_at":"2026-07-05T00:15:22.395193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03982","created_at":"2026-07-05T00:15:22.395193+00:00"},{"alias_kind":"pith_short_12","alias_value":"TU5RL2E4F6E4","created_at":"2026-07-05T00:15:22.395193+00:00"},{"alias_kind":"pith_short_16","alias_value":"TU5RL2E4F6E4WKND","created_at":"2026-07-05T00:15:22.395193+00:00"},{"alias_kind":"pith_short_8","alias_value":"TU5RL2E4","created_at":"2026-07-05T00:15:22.395193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.01847","citing_title":"Deformable Tube Network for Action Detection in Videos","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"1907.10837","citing_title":"Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17133","citing_title":"CAM-VFD: Cross-Attention Multimodal Video Forgery Detection","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16987","citing_title":"DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20311","citing_title":"Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02094","citing_title":"SignMAE: Segmentation-Driven Self-Supervised Learning for Sign Language Recognition","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TU5RL2E4F6E4WKNDMPKCXW33M2","json":"https://pith.science/pith/TU5RL2E4F6E4WKNDMPKCXW33M2.json","graph_json":"https://pith.science/api/pith-number/TU5RL2E4F6E4WKNDMPKCXW33M2/graph.json","events_json":"https://pith.science/api/pith-number/TU5RL2E4F6E4WKNDMPKCXW33M2/events.json","paper":"https://pith.science/paper/TU5RL2E4"},"agent_actions":{"view_html":"https://pith.science/pith/TU5RL2E4F6E4WKNDMPKCXW33M2","download_json":"https://pith.science/pith/TU5RL2E4F6E4WKNDMPKCXW33M2.json","view_paper":"https://pith.science/paper/TU5RL2E4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.03982&json=true","fetch_graph":"https://pith.science/api/pith-number/TU5RL2E4F6E4WKNDMPKCXW33M2/graph.json","fetch_events":"https://pith.science/api/pith-number/TU5RL2E4F6E4WKNDMPKCXW33M2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TU5RL2E4F6E4WKNDMPKCXW33M2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TU5RL2E4F6E4WKNDMPKCXW33M2/action/storage_attestation","attest_author":"https://pith.science/pith/TU5RL2E4F6E4WKNDMPKCXW33M2/action/author_attestation","sign_citation":"https://pith.science/pith/TU5RL2E4F6E4WKNDMPKCXW33M2/action/citation_signature","submit_replication":"https://pith.science/pith/TU5RL2E4F6E4WKNDMPKCXW33M2/action/replication_record"}},"created_at":"2026-07-05T00:15:22.395193+00:00","updated_at":"2026-07-05T00:15:22.395193+00:00"}