{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6ZVHSXTWLKW7HVOC36XKP3KS7H","short_pith_number":"pith:6ZVHSXTW","schema_version":"1.0","canonical_sha256":"f66a795e765aadf3d5c2dfaea7ed52f9c946ca1a80d7a45bc40dead0211d1f8c","source":{"kind":"arxiv","id":"2107.06592","version":2},"attestation_state":"computed","paper":{"title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Mike Zheng Shou, Rohan Kumar Das, Ruijie Tao, Xinyuan Qian, Zexu Pan","submitted_at":"2021-07-14T10:30:34Z","abstract_excerpt":"Active speaker detection (ASD) seeks to detect who is speaking in a visual scene of one or more speakers. The successful ASD depends on accurate interpretation of short-term and long-term audio and visual information, as well as audio-visual interaction. Unlike the prior work where systems make decision instantaneously using short-term features, we propose a novel framework, named TalkNet, that makes decision by taking both short-term and long-term features into consideration. TalkNet consists of audio and visual temporal encoders for feature representation, audio-visual cross-attention mechan"},"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":"2107.06592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-14T10:30:34Z","cross_cats_sorted":["cs.SD","eess.IV"],"title_canon_sha256":"fb418d5b334102f6de0cf10b2de9356e31c8dc9b64e52aa008001d85daab2ab1","abstract_canon_sha256":"609b717db4baf2f40908474654e8afd934fbf264b0a20ca7d58305148c3a16e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:34.742426Z","signature_b64":"ngLlhipDqVyh3ucrevQ2quAjnXiSPTdbIWV2ocR62vEVcahba+RO9qP/qW42bZVNmQyFq81iTcmvX+OlYoHDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f66a795e765aadf3d5c2dfaea7ed52f9c946ca1a80d7a45bc40dead0211d1f8c","last_reissued_at":"2026-07-05T03:00:34.742015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:34.742015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Mike Zheng Shou, Rohan Kumar Das, Ruijie Tao, Xinyuan Qian, Zexu Pan","submitted_at":"2021-07-14T10:30:34Z","abstract_excerpt":"Active speaker detection (ASD) seeks to detect who is speaking in a visual scene of one or more speakers. The successful ASD depends on accurate interpretation of short-term and long-term audio and visual information, as well as audio-visual interaction. Unlike the prior work where systems make decision instantaneously using short-term features, we propose a novel framework, named TalkNet, that makes decision by taking both short-term and long-term features into consideration. TalkNet consists of audio and visual temporal encoders for feature representation, audio-visual cross-attention mechan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06592","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/2107.06592/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":"2107.06592","created_at":"2026-07-05T03:00:34.742078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.06592v2","created_at":"2026-07-05T03:00:34.742078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06592","created_at":"2026-07-05T03:00:34.742078+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZVHSXTWLKW7","created_at":"2026-07-05T03:00:34.742078+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZVHSXTWLKW7HVOC","created_at":"2026-07-05T03:00:34.742078+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZVHSXTW","created_at":"2026-07-05T03:00:34.742078+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07294","citing_title":"Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZVHSXTWLKW7HVOC36XKP3KS7H","json":"https://pith.science/pith/6ZVHSXTWLKW7HVOC36XKP3KS7H.json","graph_json":"https://pith.science/api/pith-number/6ZVHSXTWLKW7HVOC36XKP3KS7H/graph.json","events_json":"https://pith.science/api/pith-number/6ZVHSXTWLKW7HVOC36XKP3KS7H/events.json","paper":"https://pith.science/paper/6ZVHSXTW"},"agent_actions":{"view_html":"https://pith.science/pith/6ZVHSXTWLKW7HVOC36XKP3KS7H","download_json":"https://pith.science/pith/6ZVHSXTWLKW7HVOC36XKP3KS7H.json","view_paper":"https://pith.science/paper/6ZVHSXTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.06592&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZVHSXTWLKW7HVOC36XKP3KS7H/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZVHSXTWLKW7HVOC36XKP3KS7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZVHSXTWLKW7HVOC36XKP3KS7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZVHSXTWLKW7HVOC36XKP3KS7H/action/storage_attestation","attest_author":"https://pith.science/pith/6ZVHSXTWLKW7HVOC36XKP3KS7H/action/author_attestation","sign_citation":"https://pith.science/pith/6ZVHSXTWLKW7HVOC36XKP3KS7H/action/citation_signature","submit_replication":"https://pith.science/pith/6ZVHSXTWLKW7HVOC36XKP3KS7H/action/replication_record"}},"created_at":"2026-07-05T03:00:34.742078+00:00","updated_at":"2026-07-05T03:00:34.742078+00:00"}