{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KSFVFJ3HHRYA3CEH5Z26BU3BRS","short_pith_number":"pith:KSFVFJ3H","schema_version":"1.0","canonical_sha256":"548b52a7673c700d8887ee75e0d3618c8b1c46de7d1bd4d857e5009d73386f78","source":{"kind":"arxiv","id":"2406.02831","version":2},"attestation_state":"computed","paper":{"title":"Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Dabouei, Gunjan Dhanuka, Jash Dalvi, Min Xu","submitted_at":"2024-06-05T00:44:42Z","abstract_excerpt":"Video anomaly detection aims to develop automated models capable of identifying abnormal events in surveillance videos. The benchmark setup for this task is extremely challenging due to: i) the limited size of the training sets, ii) weak supervision provided in terms of video-level labels, and iii) intrinsic class imbalance induced by the scarcity of abnormal events. In this work, we show that distilling knowledge from aggregated representations of multiple backbones into a single-backbone Student model achieves state-of-the-art performance. In particular, we develop a bi-level distillation ap"},"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":"2406.02831","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T00:44:42Z","cross_cats_sorted":[],"title_canon_sha256":"98a9cfcbf8163368df11968d4938ebb402773764b2a95b7f5d21c57e99ae82fe","abstract_canon_sha256":"797856b83c4e959e6adb6d283237821393398176935c7b69a99fd3d104db0444"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:23.338997Z","signature_b64":"1YlY+gTzhlqKqqky8TOKmVOYrVsAqAU02IvgUWI9WK5WI1js4OBxQ7D9KqSf47hoGZM0ApZk5kW3BLMfpzaBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"548b52a7673c700d8887ee75e0d3618c8b1c46de7d1bd4d857e5009d73386f78","last_reissued_at":"2026-07-05T10:02:23.338616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:23.338616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Dabouei, Gunjan Dhanuka, Jash Dalvi, Min Xu","submitted_at":"2024-06-05T00:44:42Z","abstract_excerpt":"Video anomaly detection aims to develop automated models capable of identifying abnormal events in surveillance videos. The benchmark setup for this task is extremely challenging due to: i) the limited size of the training sets, ii) weak supervision provided in terms of video-level labels, and iii) intrinsic class imbalance induced by the scarcity of abnormal events. In this work, we show that distilling knowledge from aggregated representations of multiple backbones into a single-backbone Student model achieves state-of-the-art performance. In particular, we develop a bi-level distillation ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02831","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/2406.02831/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":"2406.02831","created_at":"2026-07-05T10:02:23.338671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02831v2","created_at":"2026-07-05T10:02:23.338671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02831","created_at":"2026-07-05T10:02:23.338671+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSFVFJ3HHRYA","created_at":"2026-07-05T10:02:23.338671+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSFVFJ3HHRYA3CEH","created_at":"2026-07-05T10:02:23.338671+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSFVFJ3H","created_at":"2026-07-05T10:02:23.338671+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/KSFVFJ3HHRYA3CEH5Z26BU3BRS","json":"https://pith.science/pith/KSFVFJ3HHRYA3CEH5Z26BU3BRS.json","graph_json":"https://pith.science/api/pith-number/KSFVFJ3HHRYA3CEH5Z26BU3BRS/graph.json","events_json":"https://pith.science/api/pith-number/KSFVFJ3HHRYA3CEH5Z26BU3BRS/events.json","paper":"https://pith.science/paper/KSFVFJ3H"},"agent_actions":{"view_html":"https://pith.science/pith/KSFVFJ3HHRYA3CEH5Z26BU3BRS","download_json":"https://pith.science/pith/KSFVFJ3HHRYA3CEH5Z26BU3BRS.json","view_paper":"https://pith.science/paper/KSFVFJ3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02831&json=true","fetch_graph":"https://pith.science/api/pith-number/KSFVFJ3HHRYA3CEH5Z26BU3BRS/graph.json","fetch_events":"https://pith.science/api/pith-number/KSFVFJ3HHRYA3CEH5Z26BU3BRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSFVFJ3HHRYA3CEH5Z26BU3BRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSFVFJ3HHRYA3CEH5Z26BU3BRS/action/storage_attestation","attest_author":"https://pith.science/pith/KSFVFJ3HHRYA3CEH5Z26BU3BRS/action/author_attestation","sign_citation":"https://pith.science/pith/KSFVFJ3HHRYA3CEH5Z26BU3BRS/action/citation_signature","submit_replication":"https://pith.science/pith/KSFVFJ3HHRYA3CEH5Z26BU3BRS/action/replication_record"}},"created_at":"2026-07-05T10:02:23.338671+00:00","updated_at":"2026-07-05T10:02:23.338671+00:00"}