{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JDPV73W2S2XI7GO7F6UIPEFE2D","short_pith_number":"pith:JDPV73W2","schema_version":"1.0","canonical_sha256":"48df5feeda96ae8f99df2fa88790a4d0c12b06ddfa5aac62d3093fcc0d5685a5","source":{"kind":"arxiv","id":"2108.02607","version":1},"attestation_state":"computed","paper":{"title":"UniCon: Unified Context Network for Robust Active Speaker Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS","eess.IV"],"primary_cat":"cs.CV","authors_text":"Shiguang Shan, Shuang Yang, Susan Liang, Xiao Liu, Xilin Chen, Yuanhang Zhang, Zhongqin Wu","submitted_at":"2021-08-05T13:25:44Z","abstract_excerpt":"We introduce a new efficient framework, the Unified Context Network (UniCon), for robust active speaker detection (ASD). Traditional methods for ASD usually operate on each candidate's pre-cropped face track separately and do not sufficiently consider the relationships among the candidates. This potentially limits performance, especially in challenging scenarios with low-resolution faces, multiple candidates, etc. Our solution is a novel, unified framework that focuses on jointly modeling multiple types of contextual information: spatial context to indicate the position and scale of each candi"},"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":"2108.02607","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-05T13:25:44Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS","eess.IV"],"title_canon_sha256":"a956dc57c3d78b720d89d26c57b8f48b9894a4edcb7671ffdd186f9d1c9048ad","abstract_canon_sha256":"17ac22ce3c74464c572ed8e16bd14c43f59ca1a28c9488b08ba73533efeb051c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:34.726637Z","signature_b64":"JFfzQs4wlOqdSOc2hiBWH9FhSpCQ0kh3XZ6+v3cDLJnqeBzXFjAXC67oW0hjl6IgugAmtANDyY4WxLAZ3/pqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48df5feeda96ae8f99df2fa88790a4d0c12b06ddfa5aac62d3093fcc0d5685a5","last_reissued_at":"2026-07-05T03:03:34.726156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:34.726156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniCon: Unified Context Network for Robust Active Speaker Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS","eess.IV"],"primary_cat":"cs.CV","authors_text":"Shiguang Shan, Shuang Yang, Susan Liang, Xiao Liu, Xilin Chen, Yuanhang Zhang, Zhongqin Wu","submitted_at":"2021-08-05T13:25:44Z","abstract_excerpt":"We introduce a new efficient framework, the Unified Context Network (UniCon), for robust active speaker detection (ASD). Traditional methods for ASD usually operate on each candidate's pre-cropped face track separately and do not sufficiently consider the relationships among the candidates. This potentially limits performance, especially in challenging scenarios with low-resolution faces, multiple candidates, etc. Our solution is a novel, unified framework that focuses on jointly modeling multiple types of contextual information: spatial context to indicate the position and scale of each candi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02607","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/2108.02607/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":"2108.02607","created_at":"2026-07-05T03:03:34.726214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.02607v1","created_at":"2026-07-05T03:03:34.726214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02607","created_at":"2026-07-05T03:03:34.726214+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDPV73W2S2XI","created_at":"2026-07-05T03:03:34.726214+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDPV73W2S2XI7GO7","created_at":"2026-07-05T03:03:34.726214+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDPV73W2","created_at":"2026-07-05T03:03:34.726214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JDPV73W2S2XI7GO7F6UIPEFE2D","json":"https://pith.science/pith/JDPV73W2S2XI7GO7F6UIPEFE2D.json","graph_json":"https://pith.science/api/pith-number/JDPV73W2S2XI7GO7F6UIPEFE2D/graph.json","events_json":"https://pith.science/api/pith-number/JDPV73W2S2XI7GO7F6UIPEFE2D/events.json","paper":"https://pith.science/paper/JDPV73W2"},"agent_actions":{"view_html":"https://pith.science/pith/JDPV73W2S2XI7GO7F6UIPEFE2D","download_json":"https://pith.science/pith/JDPV73W2S2XI7GO7F6UIPEFE2D.json","view_paper":"https://pith.science/paper/JDPV73W2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.02607&json=true","fetch_graph":"https://pith.science/api/pith-number/JDPV73W2S2XI7GO7F6UIPEFE2D/graph.json","fetch_events":"https://pith.science/api/pith-number/JDPV73W2S2XI7GO7F6UIPEFE2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDPV73W2S2XI7GO7F6UIPEFE2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDPV73W2S2XI7GO7F6UIPEFE2D/action/storage_attestation","attest_author":"https://pith.science/pith/JDPV73W2S2XI7GO7F6UIPEFE2D/action/author_attestation","sign_citation":"https://pith.science/pith/JDPV73W2S2XI7GO7F6UIPEFE2D/action/citation_signature","submit_replication":"https://pith.science/pith/JDPV73W2S2XI7GO7F6UIPEFE2D/action/replication_record"}},"created_at":"2026-07-05T03:03:34.726214+00:00","updated_at":"2026-07-05T03:03:34.726214+00:00"}