{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ACMZASJEP2YHRUV7QK6VN6YGG4","short_pith_number":"pith:ACMZASJE","schema_version":"1.0","canonical_sha256":"00999049247eb078d2bf82bd56fb06371cb4759d2a25b446c65be320a983304e","source":{"kind":"arxiv","id":"2106.03932","version":2},"attestation_state":"computed","paper":{"title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Gerhard Rigoll, Maja Taseska, Okan K\\\"op\\\"ukl\\\"u","submitted_at":"2021-06-07T19:44:56Z","abstract_excerpt":"Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a reference speaker and the background speakers within each frame, and (iii) temporal modeling for the reference speaker. Each stage of this pipeline plays an important role for the final performance of the created architecture. Based on a series of controlled experiments, this work presents several practical guidelines for audio-visual active speaker detection. Correspondingly, we present a new architecture called ASDNet, whi"},"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":"2106.03932","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T19:44:56Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"d5f782a0848432432cc57778ad4e7729ac815e9055fa51382d94635884ed45b4","abstract_canon_sha256":"5a3c13d7e88dd20ac58a7dae25d450e9eddd4633d913137e23bf16dcb9faee58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:07.227773Z","signature_b64":"Y9tyZQ1p0riii2xaTas4Az1Tpxe/yJLV3vBwldYzfu0+8K+gXpqFVo3hcgWykReYVtfEgNqVSL4LX307kAvYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00999049247eb078d2bf82bd56fb06371cb4759d2a25b446c65be320a983304e","last_reissued_at":"2026-07-05T03:12:07.227312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:07.227312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Gerhard Rigoll, Maja Taseska, Okan K\\\"op\\\"ukl\\\"u","submitted_at":"2021-06-07T19:44:56Z","abstract_excerpt":"Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a reference speaker and the background speakers within each frame, and (iii) temporal modeling for the reference speaker. Each stage of this pipeline plays an important role for the final performance of the created architecture. Based on a series of controlled experiments, this work presents several practical guidelines for audio-visual active speaker detection. Correspondingly, we present a new architecture called ASDNet, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03932","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/2106.03932/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":"2106.03932","created_at":"2026-07-05T03:12:07.227390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03932v2","created_at":"2026-07-05T03:12:07.227390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03932","created_at":"2026-07-05T03:12:07.227390+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACMZASJEP2YH","created_at":"2026-07-05T03:12:07.227390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACMZASJEP2YHRUV7","created_at":"2026-07-05T03:12:07.227390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACMZASJE","created_at":"2026-07-05T03:12:07.227390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.16731","citing_title":"MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4","json":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4.json","graph_json":"https://pith.science/api/pith-number/ACMZASJEP2YHRUV7QK6VN6YGG4/graph.json","events_json":"https://pith.science/api/pith-number/ACMZASJEP2YHRUV7QK6VN6YGG4/events.json","paper":"https://pith.science/paper/ACMZASJE"},"agent_actions":{"view_html":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4","download_json":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4.json","view_paper":"https://pith.science/paper/ACMZASJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03932&json=true","fetch_graph":"https://pith.science/api/pith-number/ACMZASJEP2YHRUV7QK6VN6YGG4/graph.json","fetch_events":"https://pith.science/api/pith-number/ACMZASJEP2YHRUV7QK6VN6YGG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4/action/storage_attestation","attest_author":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4/action/author_attestation","sign_citation":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4/action/citation_signature","submit_replication":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4/action/replication_record"}},"created_at":"2026-07-05T03:12:07.227390+00:00","updated_at":"2026-07-05T03:12:07.227390+00:00"}