{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UMDHJGDI6HPUULFQ7F2Y36ZCA7","short_pith_number":"pith:UMDHJGDI","schema_version":"1.0","canonical_sha256":"a306749868f1df4a2cb0f9758dfb2207e0def15078a22745f24bf399b8043a3f","source":{"kind":"arxiv","id":"2211.15597","version":4},"attestation_state":"computed","paper":{"title":"Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","stat.ML"],"primary_cat":"cs.CV","authors_text":"Dana Dascalescu, Fahad Shahbaz Khan, Florinel-Alin Croitoru, Mubarak Shah, Nicolae-Catalin Ristea, Radu Tudor Ionescu","submitted_at":"2022-11-28T17:50:19Z","abstract_excerpt":"We propose a very fast frame-level model for anomaly detection in video, which learns to detect anomalies by distilling knowledge from multiple highly accurate object-level teacher models. To improve the fidelity of our student, we distill the low-resolution anomaly maps of the teachers by jointly applying standard and adversarial distillation, introducing an adversarial discriminator for each teacher to distinguish between target and generated anomaly maps. We conduct experiments on three benchmarks (Avenue, ShanghaiTech, UCSD Ped2), showing that our method is over 7 times faster than the fas"},"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":"2211.15597","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T17:50:19Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","stat.ML"],"title_canon_sha256":"1ff67fa9a76d71a4a1e70d78c953dc676a7631ddbc046c5585bd9ffdd724bee6","abstract_canon_sha256":"4a14d2e17356da2b774fc7135baa120fad6a810ae6ea8790e64d9cd3b9a73c70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:45.390289Z","signature_b64":"RaU6J4LzKJ59sDgqFeN5NKLj+mF69nqoqYtHsyLmDrKbQh70YfALebXfuktZPKoy5VTLximXf0qVWrd3I27EBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a306749868f1df4a2cb0f9758dfb2207e0def15078a22745f24bf399b8043a3f","last_reissued_at":"2026-07-05T08:44:45.389835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:45.389835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","stat.ML"],"primary_cat":"cs.CV","authors_text":"Dana Dascalescu, Fahad Shahbaz Khan, Florinel-Alin Croitoru, Mubarak Shah, Nicolae-Catalin Ristea, Radu Tudor Ionescu","submitted_at":"2022-11-28T17:50:19Z","abstract_excerpt":"We propose a very fast frame-level model for anomaly detection in video, which learns to detect anomalies by distilling knowledge from multiple highly accurate object-level teacher models. To improve the fidelity of our student, we distill the low-resolution anomaly maps of the teachers by jointly applying standard and adversarial distillation, introducing an adversarial discriminator for each teacher to distinguish between target and generated anomaly maps. We conduct experiments on three benchmarks (Avenue, ShanghaiTech, UCSD Ped2), showing that our method is over 7 times faster than the fas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15597","kind":"arxiv","version":4},"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/2211.15597/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":"2211.15597","created_at":"2026-07-05T08:44:45.389893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.15597v4","created_at":"2026-07-05T08:44:45.389893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15597","created_at":"2026-07-05T08:44:45.389893+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMDHJGDI6HPU","created_at":"2026-07-05T08:44:45.389893+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMDHJGDI6HPUULFQ","created_at":"2026-07-05T08:44:45.389893+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMDHJGDI","created_at":"2026-07-05T08:44:45.389893+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/UMDHJGDI6HPUULFQ7F2Y36ZCA7","json":"https://pith.science/pith/UMDHJGDI6HPUULFQ7F2Y36ZCA7.json","graph_json":"https://pith.science/api/pith-number/UMDHJGDI6HPUULFQ7F2Y36ZCA7/graph.json","events_json":"https://pith.science/api/pith-number/UMDHJGDI6HPUULFQ7F2Y36ZCA7/events.json","paper":"https://pith.science/paper/UMDHJGDI"},"agent_actions":{"view_html":"https://pith.science/pith/UMDHJGDI6HPUULFQ7F2Y36ZCA7","download_json":"https://pith.science/pith/UMDHJGDI6HPUULFQ7F2Y36ZCA7.json","view_paper":"https://pith.science/paper/UMDHJGDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.15597&json=true","fetch_graph":"https://pith.science/api/pith-number/UMDHJGDI6HPUULFQ7F2Y36ZCA7/graph.json","fetch_events":"https://pith.science/api/pith-number/UMDHJGDI6HPUULFQ7F2Y36ZCA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMDHJGDI6HPUULFQ7F2Y36ZCA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMDHJGDI6HPUULFQ7F2Y36ZCA7/action/storage_attestation","attest_author":"https://pith.science/pith/UMDHJGDI6HPUULFQ7F2Y36ZCA7/action/author_attestation","sign_citation":"https://pith.science/pith/UMDHJGDI6HPUULFQ7F2Y36ZCA7/action/citation_signature","submit_replication":"https://pith.science/pith/UMDHJGDI6HPUULFQ7F2Y36ZCA7/action/replication_record"}},"created_at":"2026-07-05T08:44:45.389893+00:00","updated_at":"2026-07-05T08:44:45.389893+00:00"}