{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QC3OKUGOM26FWJTJFLF55AOCLC","short_pith_number":"pith:QC3OKUGO","schema_version":"1.0","canonical_sha256":"80b6e550ce66bc5b26692acbde81c25885630eb2c16b1a20d6b7b9b1f455bb4e","source":{"kind":"arxiv","id":"2111.08567","version":1},"attestation_state":"computed","paper":{"title":"Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Borji, Bing Li, Mai Xu, Minglang Qiao, Weiming Hu, Xin Deng, Yufan Liu","submitted_at":"2021-11-05T14:35:08Z","abstract_excerpt":"Visual and audio events simultaneously occur and both attract attention. However, most existing saliency prediction works ignore the influence of audio and only consider vision modality. In this paper, we propose a multitask learning method for visual-audio saliency prediction and sound source localization on multi-face video by leveraging visual, audio and face information. Specifically, we first introduce a large-scale database of multi-face video in visual-audio condition (MVVA), containing eye-tracking data and sound source annotations. Using this database, we find that sound influences hu"},"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":"2111.08567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-05T14:35:08Z","cross_cats_sorted":[],"title_canon_sha256":"9c749f5f46abe287ecbfca30a1613d0206c1962ac110de296034d499db70581a","abstract_canon_sha256":"2898b6d90f3a821985b7f81048be227598358075b153a39c397efffc8b989b9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:32:35.336010Z","signature_b64":"T689NuG3jBMmocIJcmVSu2veswRltrkBPNE9pGLUppyIGL4XhsaJ3g3TodvpOSdFE7RvK/YjIZGqK+ayO0iiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80b6e550ce66bc5b26692acbde81c25885630eb2c16b1a20d6b7b9b1f455bb4e","last_reissued_at":"2026-07-05T03:32:35.335501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:32:35.335501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Borji, Bing Li, Mai Xu, Minglang Qiao, Weiming Hu, Xin Deng, Yufan Liu","submitted_at":"2021-11-05T14:35:08Z","abstract_excerpt":"Visual and audio events simultaneously occur and both attract attention. However, most existing saliency prediction works ignore the influence of audio and only consider vision modality. In this paper, we propose a multitask learning method for visual-audio saliency prediction and sound source localization on multi-face video by leveraging visual, audio and face information. Specifically, we first introduce a large-scale database of multi-face video in visual-audio condition (MVVA), containing eye-tracking data and sound source annotations. Using this database, we find that sound influences hu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08567","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/2111.08567/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":"2111.08567","created_at":"2026-07-05T03:32:35.335556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.08567v1","created_at":"2026-07-05T03:32:35.335556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08567","created_at":"2026-07-05T03:32:35.335556+00:00"},{"alias_kind":"pith_short_12","alias_value":"QC3OKUGOM26F","created_at":"2026-07-05T03:32:35.335556+00:00"},{"alias_kind":"pith_short_16","alias_value":"QC3OKUGOM26FWJTJ","created_at":"2026-07-05T03:32:35.335556+00:00"},{"alias_kind":"pith_short_8","alias_value":"QC3OKUGO","created_at":"2026-07-05T03:32:35.335556+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/QC3OKUGOM26FWJTJFLF55AOCLC","json":"https://pith.science/pith/QC3OKUGOM26FWJTJFLF55AOCLC.json","graph_json":"https://pith.science/api/pith-number/QC3OKUGOM26FWJTJFLF55AOCLC/graph.json","events_json":"https://pith.science/api/pith-number/QC3OKUGOM26FWJTJFLF55AOCLC/events.json","paper":"https://pith.science/paper/QC3OKUGO"},"agent_actions":{"view_html":"https://pith.science/pith/QC3OKUGOM26FWJTJFLF55AOCLC","download_json":"https://pith.science/pith/QC3OKUGOM26FWJTJFLF55AOCLC.json","view_paper":"https://pith.science/paper/QC3OKUGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.08567&json=true","fetch_graph":"https://pith.science/api/pith-number/QC3OKUGOM26FWJTJFLF55AOCLC/graph.json","fetch_events":"https://pith.science/api/pith-number/QC3OKUGOM26FWJTJFLF55AOCLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QC3OKUGOM26FWJTJFLF55AOCLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QC3OKUGOM26FWJTJFLF55AOCLC/action/storage_attestation","attest_author":"https://pith.science/pith/QC3OKUGOM26FWJTJFLF55AOCLC/action/author_attestation","sign_citation":"https://pith.science/pith/QC3OKUGOM26FWJTJFLF55AOCLC/action/citation_signature","submit_replication":"https://pith.science/pith/QC3OKUGOM26FWJTJFLF55AOCLC/action/replication_record"}},"created_at":"2026-07-05T03:32:35.335556+00:00","updated_at":"2026-07-05T03:32:35.335556+00:00"}