{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3VERJB6WL7KQKA3P7FOTCO3D2D","short_pith_number":"pith:3VERJB6W","schema_version":"1.0","canonical_sha256":"dd491487d65fd505036ff95d313b63d0e757ca044f9bb8835a7362780dbaff16","source":{"kind":"arxiv","id":"2208.02337","version":2},"attestation_state":"computed","paper":{"title":"Estimating Visual Information From Audio Through Manifold Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Amin Banitalebi, Dryden Wiebe, Fabrizio Pedersoli, George Tzanetakis, Kwang Moo Yi, Yong Zhang","submitted_at":"2022-08-03T20:47:11Z","abstract_excerpt":"We propose a new framework for extracting visual information about a scene only using audio signals. Audio-based methods can overcome some of the limitations of vision-based methods i.e., they do not require \"line-of-sight\", are robust to occlusions and changes in illumination, and can function as a backup in case vision/lidar sensors fail. Therefore, audio-based methods can be useful even for applications in which only visual information is of interest Our framework is based on Manifold Learning and consists of two steps. First, we train a Vector-Quantized Variational Auto-Encoder to learn th"},"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":"2208.02337","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-03T20:47:11Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"472228ecc61c3b32a03b5ae99ab7350fffe981f996789c21879bf1e0472eb351","abstract_canon_sha256":"d7f0f0f73e21bba1a7ab4b35dd413716c53885cd61b90fb153b7291fbd82f3ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:15.925403Z","signature_b64":"UIb8WAU/ExpAJrKHpOcl27Hb3SDR4RMSVRfs8U2qQgKaPduA+bJlBzlawrrlL+bNENzC67/yShTCA1X1EHtKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd491487d65fd505036ff95d313b63d0e757ca044f9bb8835a7362780dbaff16","last_reissued_at":"2026-07-05T04:57:15.924953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:15.924953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimating Visual Information From Audio Through Manifold Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Amin Banitalebi, Dryden Wiebe, Fabrizio Pedersoli, George Tzanetakis, Kwang Moo Yi, Yong Zhang","submitted_at":"2022-08-03T20:47:11Z","abstract_excerpt":"We propose a new framework for extracting visual information about a scene only using audio signals. Audio-based methods can overcome some of the limitations of vision-based methods i.e., they do not require \"line-of-sight\", are robust to occlusions and changes in illumination, and can function as a backup in case vision/lidar sensors fail. Therefore, audio-based methods can be useful even for applications in which only visual information is of interest Our framework is based on Manifold Learning and consists of two steps. First, we train a Vector-Quantized Variational Auto-Encoder to learn th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.02337","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/2208.02337/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":"2208.02337","created_at":"2026-07-05T04:57:15.925008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.02337v2","created_at":"2026-07-05T04:57:15.925008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.02337","created_at":"2026-07-05T04:57:15.925008+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VERJB6WL7KQ","created_at":"2026-07-05T04:57:15.925008+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VERJB6WL7KQKA3P","created_at":"2026-07-05T04:57:15.925008+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VERJB6W","created_at":"2026-07-05T04:57:15.925008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14935","citing_title":"Open-set Cross Modal Generalization via Multimodal Unified Representation","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VERJB6WL7KQKA3P7FOTCO3D2D","json":"https://pith.science/pith/3VERJB6WL7KQKA3P7FOTCO3D2D.json","graph_json":"https://pith.science/api/pith-number/3VERJB6WL7KQKA3P7FOTCO3D2D/graph.json","events_json":"https://pith.science/api/pith-number/3VERJB6WL7KQKA3P7FOTCO3D2D/events.json","paper":"https://pith.science/paper/3VERJB6W"},"agent_actions":{"view_html":"https://pith.science/pith/3VERJB6WL7KQKA3P7FOTCO3D2D","download_json":"https://pith.science/pith/3VERJB6WL7KQKA3P7FOTCO3D2D.json","view_paper":"https://pith.science/paper/3VERJB6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.02337&json=true","fetch_graph":"https://pith.science/api/pith-number/3VERJB6WL7KQKA3P7FOTCO3D2D/graph.json","fetch_events":"https://pith.science/api/pith-number/3VERJB6WL7KQKA3P7FOTCO3D2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VERJB6WL7KQKA3P7FOTCO3D2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VERJB6WL7KQKA3P7FOTCO3D2D/action/storage_attestation","attest_author":"https://pith.science/pith/3VERJB6WL7KQKA3P7FOTCO3D2D/action/author_attestation","sign_citation":"https://pith.science/pith/3VERJB6WL7KQKA3P7FOTCO3D2D/action/citation_signature","submit_replication":"https://pith.science/pith/3VERJB6WL7KQKA3P7FOTCO3D2D/action/replication_record"}},"created_at":"2026-07-05T04:57:15.925008+00:00","updated_at":"2026-07-05T04:57:15.925008+00:00"}