{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XFLGSQTB2C75ILF3V7CGDWPW6K","short_pith_number":"pith:XFLGSQTB","schema_version":"1.0","canonical_sha256":"b956694261d0bfd42cbbafc461d9f6f2b8d7df45371af13fef2c70ded85f1d7b","source":{"kind":"arxiv","id":"2307.04760","version":4},"attestation_state":"computed","paper":{"title":"Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Kristen Grauman, Sagnik Majumder, Ziad Al-Halah","submitted_at":"2023-07-10T17:58:17Z","abstract_excerpt":"We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. Our method uses a masked auto-encoding framework to synthesize masked binaural (multi-channel) audio through the synergy of audio and vision, thereby learning useful spatial relationships between the two modalities. We use our pretrained features to tackle two downstream video tasks requiring spatial understanding in social scenarios: active speaker detection and spatial audio denoising. Through extensive experiments, we show that our features are generic enough "},"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":"2307.04760","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-10T17:58:17Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"cacbca172d15fe1b13e298014fa6bce82f555b115cd9a555c80798de62a7d627","abstract_canon_sha256":"b17f65f7409b49d8e592fc39b23ef314d055006543fc1e8414b147e5249f2302"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:37.983567Z","signature_b64":"HPp8jZGpjeBjgE7aCXE80moxCol/sE4X5BalGEr80l6R5/g1uXKiZuRlOTfLTwxyRBW2OCQMy4BubsFIgY28Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b956694261d0bfd42cbbafc461d9f6f2b8d7df45371af13fef2c70ded85f1d7b","last_reissued_at":"2026-07-05T08:15:37.983069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:37.983069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Kristen Grauman, Sagnik Majumder, Ziad Al-Halah","submitted_at":"2023-07-10T17:58:17Z","abstract_excerpt":"We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. Our method uses a masked auto-encoding framework to synthesize masked binaural (multi-channel) audio through the synergy of audio and vision, thereby learning useful spatial relationships between the two modalities. We use our pretrained features to tackle two downstream video tasks requiring spatial understanding in social scenarios: active speaker detection and spatial audio denoising. Through extensive experiments, we show that our features are generic enough "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04760","kind":"arxiv","version":4},"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/2307.04760/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":"2307.04760","created_at":"2026-07-05T08:15:37.983120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04760v4","created_at":"2026-07-05T08:15:37.983120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04760","created_at":"2026-07-05T08:15:37.983120+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFLGSQTB2C75","created_at":"2026-07-05T08:15:37.983120+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFLGSQTB2C75ILF3","created_at":"2026-07-05T08:15:37.983120+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFLGSQTB","created_at":"2026-07-05T08:15:37.983120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17698","citing_title":"Video-Guided Foley Sound Generation with Multimodal Controls","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFLGSQTB2C75ILF3V7CGDWPW6K","json":"https://pith.science/pith/XFLGSQTB2C75ILF3V7CGDWPW6K.json","graph_json":"https://pith.science/api/pith-number/XFLGSQTB2C75ILF3V7CGDWPW6K/graph.json","events_json":"https://pith.science/api/pith-number/XFLGSQTB2C75ILF3V7CGDWPW6K/events.json","paper":"https://pith.science/paper/XFLGSQTB"},"agent_actions":{"view_html":"https://pith.science/pith/XFLGSQTB2C75ILF3V7CGDWPW6K","download_json":"https://pith.science/pith/XFLGSQTB2C75ILF3V7CGDWPW6K.json","view_paper":"https://pith.science/paper/XFLGSQTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04760&json=true","fetch_graph":"https://pith.science/api/pith-number/XFLGSQTB2C75ILF3V7CGDWPW6K/graph.json","fetch_events":"https://pith.science/api/pith-number/XFLGSQTB2C75ILF3V7CGDWPW6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFLGSQTB2C75ILF3V7CGDWPW6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFLGSQTB2C75ILF3V7CGDWPW6K/action/storage_attestation","attest_author":"https://pith.science/pith/XFLGSQTB2C75ILF3V7CGDWPW6K/action/author_attestation","sign_citation":"https://pith.science/pith/XFLGSQTB2C75ILF3V7CGDWPW6K/action/citation_signature","submit_replication":"https://pith.science/pith/XFLGSQTB2C75ILF3V7CGDWPW6K/action/replication_record"}},"created_at":"2026-07-05T08:15:37.983120+00:00","updated_at":"2026-07-05T08:15:37.983120+00:00"}