{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JDPV73W2S2XI7GO7F6UIPEFE2D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"17ac22ce3c74464c572ed8e16bd14c43f59ca1a28c9488b08ba73533efeb051c","cross_cats_sorted":["cs.MM","cs.SD","eess.AS","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-05T13:25:44Z","title_canon_sha256":"a956dc57c3d78b720d89d26c57b8f48b9894a4edcb7671ffdd186f9d1c9048ad"},"schema_version":"1.0","source":{"id":"2108.02607","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02607","created_at":"2026-07-05T03:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02607v1","created_at":"2026-07-05T03:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02607","created_at":"2026-07-05T03:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"JDPV73W2S2XI","created_at":"2026-07-05T03:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"JDPV73W2S2XI7GO7","created_at":"2026-07-05T03:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"JDPV73W2","created_at":"2026-07-05T03:03:34Z"}],"graph_snapshots":[{"event_id":"sha256:c72a541072244425a8c08e9839fe6f1fbc237607e655482962f122b379db96d6","target":"graph","created_at":"2026-07-05T03:03:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.02607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Shiguang Shan, Shuang Yang, Susan Liang, Xiao Liu, Xilin Chen, Yuanhang Zhang, Zhongqin Wu","cross_cats":["cs.MM","cs.SD","eess.AS","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-05T13:25:44Z","title":"UniCon: Unified Context Network for Robust Active Speaker Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02607","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7eeb199dee2fe723a04cb6975954443e4fe1c19071ac81cc595df8d12b713c83","target":"record","created_at":"2026-07-05T03:03:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"17ac22ce3c74464c572ed8e16bd14c43f59ca1a28c9488b08ba73533efeb051c","cross_cats_sorted":["cs.MM","cs.SD","eess.AS","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-05T13:25:44Z","title_canon_sha256":"a956dc57c3d78b720d89d26c57b8f48b9894a4edcb7671ffdd186f9d1c9048ad"},"schema_version":"1.0","source":{"id":"2108.02607","kind":"arxiv","version":1}},"canonical_sha256":"48df5feeda96ae8f99df2fa88790a4d0c12b06ddfa5aac62d3093fcc0d5685a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48df5feeda96ae8f99df2fa88790a4d0c12b06ddfa5aac62d3093fcc0d5685a5","first_computed_at":"2026-07-05T03:03:34.726156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:34.726156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JFfzQs4wlOqdSOc2hiBWH9FhSpCQ0kh3XZ6+v3cDLJnqeBzXFjAXC67oW0hjl6IgugAmtANDyY4WxLAZ3/pqBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:34.726637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.02607","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eeb199dee2fe723a04cb6975954443e4fe1c19071ac81cc595df8d12b713c83","sha256:c72a541072244425a8c08e9839fe6f1fbc237607e655482962f122b379db96d6"],"state_sha256":"d5e5f46ae094078f11862a9e30f08b27872ad85d055cc6972c6a2529912865d6"}