{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NDFZMOVCJ35KMUJ5C2PIUS2GE5","short_pith_number":"pith:NDFZMOVC","schema_version":"1.0","canonical_sha256":"68cb963aa24efaa6513d169e8a4b4627759d02ae1cb94b77b28d2d27dc1a349e","source":{"kind":"arxiv","id":"2409.14109","version":2},"attestation_state":"computed","paper":{"title":"Vision-Language Models Assisted Unsupervised Video Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liquan Mao, Yalong Jiang","submitted_at":"2024-09-21T11:48:54Z","abstract_excerpt":"Video anomaly detection is a subject of great interest across industrial and academic domains due to its crucial role in computer vision applications. However, the inherent unpredictability of anomalies and the scarcity of anomaly samples present significant challenges for unsupervised learning methods. To overcome the limitations of unsupervised learning, which stem from a lack of comprehensive prior knowledge about anomalies, we propose VLAVAD (Video-Language Models Assisted Anomaly Detection). Our method employs a cross-modal pre-trained model that leverages the inferential capabilities of "},"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":"2409.14109","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-21T11:48:54Z","cross_cats_sorted":[],"title_canon_sha256":"5eeff26b3ff7017a33ef3dc6393c888b2a56541b52f65359730a2622e0e9a093","abstract_canon_sha256":"e81f2b726e866791e782d5e2f3e510cd838b8d4d5b97f255fa3b1374c6810a66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:48.434865Z","signature_b64":"XqSjvYWPZT+HgLAER1VEUaSeVcvE6COAQ+IbS/M9MB7yjSZZ7NYP/uYTitHZ4JgsxUTCfJbQ26y+9Ern/6xLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68cb963aa24efaa6513d169e8a4b4627759d02ae1cb94b77b28d2d27dc1a349e","last_reissued_at":"2026-07-05T09:11:48.434425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:48.434425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Models Assisted Unsupervised Video Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liquan Mao, Yalong Jiang","submitted_at":"2024-09-21T11:48:54Z","abstract_excerpt":"Video anomaly detection is a subject of great interest across industrial and academic domains due to its crucial role in computer vision applications. However, the inherent unpredictability of anomalies and the scarcity of anomaly samples present significant challenges for unsupervised learning methods. To overcome the limitations of unsupervised learning, which stem from a lack of comprehensive prior knowledge about anomalies, we propose VLAVAD (Video-Language Models Assisted Anomaly Detection). Our method employs a cross-modal pre-trained model that leverages the inferential capabilities of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14109","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.14109/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":"2409.14109","created_at":"2026-07-05T09:11:48.434486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14109v2","created_at":"2026-07-05T09:11:48.434486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14109","created_at":"2026-07-05T09:11:48.434486+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDFZMOVCJ35K","created_at":"2026-07-05T09:11:48.434486+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDFZMOVCJ35KMUJ5","created_at":"2026-07-05T09:11:48.434486+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDFZMOVC","created_at":"2026-07-05T09:11:48.434486+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21649","citing_title":"The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM","ref_index":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDFZMOVCJ35KMUJ5C2PIUS2GE5","json":"https://pith.science/pith/NDFZMOVCJ35KMUJ5C2PIUS2GE5.json","graph_json":"https://pith.science/api/pith-number/NDFZMOVCJ35KMUJ5C2PIUS2GE5/graph.json","events_json":"https://pith.science/api/pith-number/NDFZMOVCJ35KMUJ5C2PIUS2GE5/events.json","paper":"https://pith.science/paper/NDFZMOVC"},"agent_actions":{"view_html":"https://pith.science/pith/NDFZMOVCJ35KMUJ5C2PIUS2GE5","download_json":"https://pith.science/pith/NDFZMOVCJ35KMUJ5C2PIUS2GE5.json","view_paper":"https://pith.science/paper/NDFZMOVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14109&json=true","fetch_graph":"https://pith.science/api/pith-number/NDFZMOVCJ35KMUJ5C2PIUS2GE5/graph.json","fetch_events":"https://pith.science/api/pith-number/NDFZMOVCJ35KMUJ5C2PIUS2GE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDFZMOVCJ35KMUJ5C2PIUS2GE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDFZMOVCJ35KMUJ5C2PIUS2GE5/action/storage_attestation","attest_author":"https://pith.science/pith/NDFZMOVCJ35KMUJ5C2PIUS2GE5/action/author_attestation","sign_citation":"https://pith.science/pith/NDFZMOVCJ35KMUJ5C2PIUS2GE5/action/citation_signature","submit_replication":"https://pith.science/pith/NDFZMOVCJ35KMUJ5C2PIUS2GE5/action/replication_record"}},"created_at":"2026-07-05T09:11:48.434486+00:00","updated_at":"2026-07-05T09:11:48.434486+00:00"}