{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B5DANK3FOLPSR3ME33MWNFNWUM","short_pith_number":"pith:B5DANK3F","schema_version":"1.0","canonical_sha256":"0f4606ab6572df28ed84ded96695b6a314b36e60eb03ab112e5c0ef6adc752a1","source":{"kind":"arxiv","id":"2505.02393","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty-Weighted Image-Event Multimodal Fusion for Video Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jihong Park, Mohsen Imani, Sungheon Jeong","submitted_at":"2025-05-05T06:33:20Z","abstract_excerpt":"Most existing video anomaly detectors rely solely on RGB frames, which lack the temporal resolution needed to capture abrupt or transient motion cues, key indicators of anomalous events. To address this limitation, we propose Image-Event Fusion for Video Anomaly Detection (IEF-VAD), a framework that synthesizes event representations directly from RGB videos and fuses them with image features through a principled, uncertainty-aware process. The system (i) models heavy-tailed sensor noise with a Student`s-t likelihood, deriving value-level inverse-variance weights via a Laplace approximation; (i"},"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":"2505.02393","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-05T06:33:20Z","cross_cats_sorted":[],"title_canon_sha256":"b6a014197367e5e57e34de2edd185a93e24df83c36b3d08f4d6a86b9e262f312","abstract_canon_sha256":"19c95880785b9899e166a337e43434abc53429128949fe25ffbe03c62d5e00c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:07.622390Z","signature_b64":"wiVxKjRelP8eRjXNOR/XHrJ4xhWTM0QgTr4VEOrfX049h9UPinEY+5Het8oiBecE8Djh6TN55DX8bms4WWULDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f4606ab6572df28ed84ded96695b6a314b36e60eb03ab112e5c0ef6adc752a1","last_reissued_at":"2026-07-05T11:00:07.621899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:07.621899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Weighted Image-Event Multimodal Fusion for Video Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jihong Park, Mohsen Imani, Sungheon Jeong","submitted_at":"2025-05-05T06:33:20Z","abstract_excerpt":"Most existing video anomaly detectors rely solely on RGB frames, which lack the temporal resolution needed to capture abrupt or transient motion cues, key indicators of anomalous events. To address this limitation, we propose Image-Event Fusion for Video Anomaly Detection (IEF-VAD), a framework that synthesizes event representations directly from RGB videos and fuses them with image features through a principled, uncertainty-aware process. The system (i) models heavy-tailed sensor noise with a Student`s-t likelihood, deriving value-level inverse-variance weights via a Laplace approximation; (i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02393","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/2505.02393/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":"2505.02393","created_at":"2026-07-05T11:00:07.621957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02393v2","created_at":"2026-07-05T11:00:07.621957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02393","created_at":"2026-07-05T11:00:07.621957+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5DANK3FOLPS","created_at":"2026-07-05T11:00:07.621957+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5DANK3FOLPSR3ME","created_at":"2026-07-05T11:00:07.621957+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5DANK3F","created_at":"2026-07-05T11:00:07.621957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08651","citing_title":"Privacy-Aware Video Anomaly Detection through Orthogonal Subspace Projection","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5DANK3FOLPSR3ME33MWNFNWUM","json":"https://pith.science/pith/B5DANK3FOLPSR3ME33MWNFNWUM.json","graph_json":"https://pith.science/api/pith-number/B5DANK3FOLPSR3ME33MWNFNWUM/graph.json","events_json":"https://pith.science/api/pith-number/B5DANK3FOLPSR3ME33MWNFNWUM/events.json","paper":"https://pith.science/paper/B5DANK3F"},"agent_actions":{"view_html":"https://pith.science/pith/B5DANK3FOLPSR3ME33MWNFNWUM","download_json":"https://pith.science/pith/B5DANK3FOLPSR3ME33MWNFNWUM.json","view_paper":"https://pith.science/paper/B5DANK3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02393&json=true","fetch_graph":"https://pith.science/api/pith-number/B5DANK3FOLPSR3ME33MWNFNWUM/graph.json","fetch_events":"https://pith.science/api/pith-number/B5DANK3FOLPSR3ME33MWNFNWUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5DANK3FOLPSR3ME33MWNFNWUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5DANK3FOLPSR3ME33MWNFNWUM/action/storage_attestation","attest_author":"https://pith.science/pith/B5DANK3FOLPSR3ME33MWNFNWUM/action/author_attestation","sign_citation":"https://pith.science/pith/B5DANK3FOLPSR3ME33MWNFNWUM/action/citation_signature","submit_replication":"https://pith.science/pith/B5DANK3FOLPSR3ME33MWNFNWUM/action/replication_record"}},"created_at":"2026-07-05T11:00:07.621957+00:00","updated_at":"2026-07-05T11:00:07.621957+00:00"}