{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WGAKUSJZKAVHLGF77TJHRMR7ZH","short_pith_number":"pith:WGAKUSJZ","schema_version":"1.0","canonical_sha256":"b180aa4939502a7598bffcd278b23fc9db6ca689decec8f558cc901404b1f45f","source":{"kind":"arxiv","id":"2207.03048","version":2},"attestation_state":"computed","paper":{"title":"AV-Gaze: A Study on the Effectiveness of Audio Guided Visual Attention Estimation for Non-Profilic Faces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Dhall, Jarrod Knibbe, Munawar Hayat, Shreya Ghosh","submitted_at":"2022-07-07T02:23:02Z","abstract_excerpt":"In challenging real-life conditions such as extreme head-pose, occlusions, and low-resolution images where the visual information fails to estimate visual attention/gaze direction, audio signals could provide important and complementary information. In this paper, we explore if audio-guided coarse head-pose can further enhance visual attention estimation performance for non-prolific faces. Since it is difficult to annotate audio signals for estimating the head-pose of the speaker, we use off-the-shelf state-of-the-art models to facilitate cross-modal weak-supervision. During the training phase"},"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":"2207.03048","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T02:23:02Z","cross_cats_sorted":[],"title_canon_sha256":"02aafa3a48c5e5f9cef0380ec2aeb1139f605f5d5d1e0b2dd1480a40c4649a8e","abstract_canon_sha256":"c2a5a5d8afc286a94847096ac32246928265c8af9ebda25658621db4c8e06f26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:47:59.035329Z","signature_b64":"a+25uTJdTZGJRB3cDfr5lfB9YA7uxQf8IB06cOJNy+Tm+zbeVJhEn8vvhy4uEwOB5e6cnpOU1z3sdCe0j2AlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b180aa4939502a7598bffcd278b23fc9db6ca689decec8f558cc901404b1f45f","last_reissued_at":"2026-07-05T04:47:59.034900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:47:59.034900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AV-Gaze: A Study on the Effectiveness of Audio Guided Visual Attention Estimation for Non-Profilic Faces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Dhall, Jarrod Knibbe, Munawar Hayat, Shreya Ghosh","submitted_at":"2022-07-07T02:23:02Z","abstract_excerpt":"In challenging real-life conditions such as extreme head-pose, occlusions, and low-resolution images where the visual information fails to estimate visual attention/gaze direction, audio signals could provide important and complementary information. In this paper, we explore if audio-guided coarse head-pose can further enhance visual attention estimation performance for non-prolific faces. Since it is difficult to annotate audio signals for estimating the head-pose of the speaker, we use off-the-shelf state-of-the-art models to facilitate cross-modal weak-supervision. During the training phase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03048","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/2207.03048/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":"2207.03048","created_at":"2026-07-05T04:47:59.034954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.03048v2","created_at":"2026-07-05T04:47:59.034954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03048","created_at":"2026-07-05T04:47:59.034954+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGAKUSJZKAVH","created_at":"2026-07-05T04:47:59.034954+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGAKUSJZKAVHLGF7","created_at":"2026-07-05T04:47:59.034954+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGAKUSJZ","created_at":"2026-07-05T04:47:59.034954+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/WGAKUSJZKAVHLGF77TJHRMR7ZH","json":"https://pith.science/pith/WGAKUSJZKAVHLGF77TJHRMR7ZH.json","graph_json":"https://pith.science/api/pith-number/WGAKUSJZKAVHLGF77TJHRMR7ZH/graph.json","events_json":"https://pith.science/api/pith-number/WGAKUSJZKAVHLGF77TJHRMR7ZH/events.json","paper":"https://pith.science/paper/WGAKUSJZ"},"agent_actions":{"view_html":"https://pith.science/pith/WGAKUSJZKAVHLGF77TJHRMR7ZH","download_json":"https://pith.science/pith/WGAKUSJZKAVHLGF77TJHRMR7ZH.json","view_paper":"https://pith.science/paper/WGAKUSJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.03048&json=true","fetch_graph":"https://pith.science/api/pith-number/WGAKUSJZKAVHLGF77TJHRMR7ZH/graph.json","fetch_events":"https://pith.science/api/pith-number/WGAKUSJZKAVHLGF77TJHRMR7ZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGAKUSJZKAVHLGF77TJHRMR7ZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGAKUSJZKAVHLGF77TJHRMR7ZH/action/storage_attestation","attest_author":"https://pith.science/pith/WGAKUSJZKAVHLGF77TJHRMR7ZH/action/author_attestation","sign_citation":"https://pith.science/pith/WGAKUSJZKAVHLGF77TJHRMR7ZH/action/citation_signature","submit_replication":"https://pith.science/pith/WGAKUSJZKAVHLGF77TJHRMR7ZH/action/replication_record"}},"created_at":"2026-07-05T04:47:59.034954+00:00","updated_at":"2026-07-05T04:47:59.034954+00:00"}