{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZI2F4MQERPLZXJNDOH6NFLSTTK","short_pith_number":"pith:ZI2F4MQE","schema_version":"1.0","canonical_sha256":"ca345e32048bd79ba5a371fcd2ae539abb1a3581c3ec5ac6b5418dd571855e01","source":{"kind":"arxiv","id":"2110.13412","version":1},"attestation_state":"computed","paper":{"title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Leonid Sigal, Mengyu Yang, Tanzila Rahman","submitted_at":"2021-10-26T04:50:42Z","abstract_excerpt":"The recent success of transformer models in language, such as BERT, has motivated the use of such architectures for multi-modal feature learning and tasks. However, most multi-modal variants (e.g., ViLBERT) have limited themselves to visual-linguistic data. Relatively few have explored its use in audio-visual modalities, and none, to our knowledge, illustrate them in the context of granular audio-visual detection or segmentation tasks such as sound source separation and localization. In this work, we introduce TriBERT -- a transformer-based architecture, inspired by ViLBERT, which enables cont"},"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":"2110.13412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T04:50:42Z","cross_cats_sorted":[],"title_canon_sha256":"87b7d9be98904ca89e34c1c91354ae7c70ff13acd2ecebfdfa66581d47e1ad4e","abstract_canon_sha256":"68396053bc54ed5c2a64865cc5c006cf7eeafe20186f5a3565bca37ce0e80aff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:38.556833Z","signature_b64":"6TczvvouxWmeHAD6DTlGUsgqQ4W1N67LkTo0rXrE7cy/rlDm1yPi3FzY3lizvPJIPbbp9L8/kYe5JukuMJZVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca345e32048bd79ba5a371fcd2ae539abb1a3581c3ec5ac6b5418dd571855e01","last_reissued_at":"2026-07-05T03:25:38.556483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:38.556483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Leonid Sigal, Mengyu Yang, Tanzila Rahman","submitted_at":"2021-10-26T04:50:42Z","abstract_excerpt":"The recent success of transformer models in language, such as BERT, has motivated the use of such architectures for multi-modal feature learning and tasks. However, most multi-modal variants (e.g., ViLBERT) have limited themselves to visual-linguistic data. Relatively few have explored its use in audio-visual modalities, and none, to our knowledge, illustrate them in the context of granular audio-visual detection or segmentation tasks such as sound source separation and localization. In this work, we introduce TriBERT -- a transformer-based architecture, inspired by ViLBERT, which enables cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13412","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/2110.13412/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":"2110.13412","created_at":"2026-07-05T03:25:38.556544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.13412v1","created_at":"2026-07-05T03:25:38.556544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13412","created_at":"2026-07-05T03:25:38.556544+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZI2F4MQERPLZ","created_at":"2026-07-05T03:25:38.556544+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZI2F4MQERPLZXJND","created_at":"2026-07-05T03:25:38.556544+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZI2F4MQE","created_at":"2026-07-05T03:25:38.556544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.21366","citing_title":"DGFNet: End-to-End Audio-Visual Source Separation Based on Dynamic Gating Fusion","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK","json":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK.json","graph_json":"https://pith.science/api/pith-number/ZI2F4MQERPLZXJNDOH6NFLSTTK/graph.json","events_json":"https://pith.science/api/pith-number/ZI2F4MQERPLZXJNDOH6NFLSTTK/events.json","paper":"https://pith.science/paper/ZI2F4MQE"},"agent_actions":{"view_html":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK","download_json":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK.json","view_paper":"https://pith.science/paper/ZI2F4MQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.13412&json=true","fetch_graph":"https://pith.science/api/pith-number/ZI2F4MQERPLZXJNDOH6NFLSTTK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZI2F4MQERPLZXJNDOH6NFLSTTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK/action/storage_attestation","attest_author":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK/action/author_attestation","sign_citation":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK/action/citation_signature","submit_replication":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK/action/replication_record"}},"created_at":"2026-07-05T03:25:38.556544+00:00","updated_at":"2026-07-05T03:25:38.556544+00:00"}