{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EAVCUYRKMSU3JR2YEYOSNQ3TK2","short_pith_number":"pith:EAVCUYRK","schema_version":"1.0","canonical_sha256":"202a2a622a64a9b4c758261d26c37356810dffe785cd7d697636376bedeba572","source":{"kind":"arxiv","id":"2411.11454","version":1},"attestation_state":"computed","paper":{"title":"Relevance-guided Audio Visual Fusion for Video Saliency Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Yu, Moncef Gabbouj, Pan Gao, Xuanzhe Sun","submitted_at":"2024-11-18T10:42:27Z","abstract_excerpt":"Audio data, often synchronized with video frames, plays a crucial role in guiding the audience's visual attention. Incorporating audio information into video saliency prediction tasks can enhance the prediction of human visual behavior. However, existing audio-visual saliency prediction methods often directly fuse audio and visual features, which ignore the possibility of inconsistency between the two modalities, such as when the audio serves as background music. To address this issue, we propose a novel relevance-guided audio-visual saliency prediction network dubbed AVRSP. Specifically, the "},"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":"2411.11454","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T10:42:27Z","cross_cats_sorted":[],"title_canon_sha256":"04d1f911255a46bb818cc8c92c4a6cf3fccbc969cf7a1511b2c0b05c13d00867","abstract_canon_sha256":"f6beddb9bc4e1ba0d14b2c854c26497f6f71a010997ed0905231b9c678629d89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:56.577930Z","signature_b64":"FxP1ozcMl8kvws9turbeVC/eCkKbzY2CyqjUzVE+vjCu2pfzwz03Y4xOGTVJjVKEpX99EPXbPbKHczLnRzRDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"202a2a622a64a9b4c758261d26c37356810dffe785cd7d697636376bedeba572","last_reissued_at":"2026-07-05T09:36:56.577509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:56.577509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relevance-guided Audio Visual Fusion for Video Saliency Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Yu, Moncef Gabbouj, Pan Gao, Xuanzhe Sun","submitted_at":"2024-11-18T10:42:27Z","abstract_excerpt":"Audio data, often synchronized with video frames, plays a crucial role in guiding the audience's visual attention. Incorporating audio information into video saliency prediction tasks can enhance the prediction of human visual behavior. However, existing audio-visual saliency prediction methods often directly fuse audio and visual features, which ignore the possibility of inconsistency between the two modalities, such as when the audio serves as background music. To address this issue, we propose a novel relevance-guided audio-visual saliency prediction network dubbed AVRSP. Specifically, the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11454","kind":"arxiv","version":1},"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/2411.11454/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":"2411.11454","created_at":"2026-07-05T09:36:56.577562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11454v1","created_at":"2026-07-05T09:36:56.577562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11454","created_at":"2026-07-05T09:36:56.577562+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAVCUYRKMSU3","created_at":"2026-07-05T09:36:56.577562+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAVCUYRKMSU3JR2Y","created_at":"2026-07-05T09:36:56.577562+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAVCUYRK","created_at":"2026-07-05T09:36:56.577562+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/EAVCUYRKMSU3JR2YEYOSNQ3TK2","json":"https://pith.science/pith/EAVCUYRKMSU3JR2YEYOSNQ3TK2.json","graph_json":"https://pith.science/api/pith-number/EAVCUYRKMSU3JR2YEYOSNQ3TK2/graph.json","events_json":"https://pith.science/api/pith-number/EAVCUYRKMSU3JR2YEYOSNQ3TK2/events.json","paper":"https://pith.science/paper/EAVCUYRK"},"agent_actions":{"view_html":"https://pith.science/pith/EAVCUYRKMSU3JR2YEYOSNQ3TK2","download_json":"https://pith.science/pith/EAVCUYRKMSU3JR2YEYOSNQ3TK2.json","view_paper":"https://pith.science/paper/EAVCUYRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11454&json=true","fetch_graph":"https://pith.science/api/pith-number/EAVCUYRKMSU3JR2YEYOSNQ3TK2/graph.json","fetch_events":"https://pith.science/api/pith-number/EAVCUYRKMSU3JR2YEYOSNQ3TK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAVCUYRKMSU3JR2YEYOSNQ3TK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAVCUYRKMSU3JR2YEYOSNQ3TK2/action/storage_attestation","attest_author":"https://pith.science/pith/EAVCUYRKMSU3JR2YEYOSNQ3TK2/action/author_attestation","sign_citation":"https://pith.science/pith/EAVCUYRKMSU3JR2YEYOSNQ3TK2/action/citation_signature","submit_replication":"https://pith.science/pith/EAVCUYRKMSU3JR2YEYOSNQ3TK2/action/replication_record"}},"created_at":"2026-07-05T09:36:56.577562+00:00","updated_at":"2026-07-05T09:36:56.577562+00:00"}