{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NB5FUT3SX7MEHLHVGR2AWYRAM3","short_pith_number":"pith:NB5FUT3S","schema_version":"1.0","canonical_sha256":"687a5a4f72bfd843acf534740b622066e2754586ae2410e1522bf11ea28905e7","source":{"kind":"arxiv","id":"2408.14585","version":2},"attestation_state":"computed","paper":{"title":"Global-Local Distillation Network-Based Audio-Visual Speaker Tracking with Incomplete Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bin Ren, Hao Guo, Hong Liu, Nicu Sebe, Yidi Li, Yihan Li, Yixin Guo, Zhenhuan Xu","submitted_at":"2024-08-26T19:09:21Z","abstract_excerpt":"In speaker tracking research, integrating and complementing multi-modal data is a crucial strategy for improving the accuracy and robustness of tracking systems. However, tracking with incomplete modalities remains a challenging issue due to noisy observations caused by occlusion, acoustic noise, and sensor failures. Especially when there is missing data in multiple modalities, the performance of existing multi-modal fusion methods tends to decrease. To this end, we propose a Global-Local Distillation-based Tracker (GLDTracker) for robust audio-visual speaker tracking. GLDTracker is driven by "},"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":"2408.14585","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T19:09:21Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4cb77bc43c4da3ceda0b4dabe0768c0871579c65b12900247ab952a2c15fe5ae","abstract_canon_sha256":"5af7e8f317d1095f12da716d3e54c3fab9a02e1c95a62696769802a1f6f30bb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:19.023859Z","signature_b64":"0BcW9aIiXgvzDnkOwbG/dqvmTLHGFFX9VKTgT9Yn653xlTylLGyVlJoHJsTuueYvdTRoGpFB0tFiCz8hT5ubBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"687a5a4f72bfd843acf534740b622066e2754586ae2410e1522bf11ea28905e7","last_reissued_at":"2026-07-05T10:15:19.023377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:19.023377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global-Local Distillation Network-Based Audio-Visual Speaker Tracking with Incomplete Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bin Ren, Hao Guo, Hong Liu, Nicu Sebe, Yidi Li, Yihan Li, Yixin Guo, Zhenhuan Xu","submitted_at":"2024-08-26T19:09:21Z","abstract_excerpt":"In speaker tracking research, integrating and complementing multi-modal data is a crucial strategy for improving the accuracy and robustness of tracking systems. However, tracking with incomplete modalities remains a challenging issue due to noisy observations caused by occlusion, acoustic noise, and sensor failures. Especially when there is missing data in multiple modalities, the performance of existing multi-modal fusion methods tends to decrease. To this end, we propose a Global-Local Distillation-based Tracker (GLDTracker) for robust audio-visual speaker tracking. GLDTracker is driven by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14585","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/2408.14585/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":"2408.14585","created_at":"2026-07-05T10:15:19.023428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14585v2","created_at":"2026-07-05T10:15:19.023428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14585","created_at":"2026-07-05T10:15:19.023428+00:00"},{"alias_kind":"pith_short_12","alias_value":"NB5FUT3SX7ME","created_at":"2026-07-05T10:15:19.023428+00:00"},{"alias_kind":"pith_short_16","alias_value":"NB5FUT3SX7MEHLHV","created_at":"2026-07-05T10:15:19.023428+00:00"},{"alias_kind":"pith_short_8","alias_value":"NB5FUT3S","created_at":"2026-07-05T10:15:19.023428+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/NB5FUT3SX7MEHLHVGR2AWYRAM3","json":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3.json","graph_json":"https://pith.science/api/pith-number/NB5FUT3SX7MEHLHVGR2AWYRAM3/graph.json","events_json":"https://pith.science/api/pith-number/NB5FUT3SX7MEHLHVGR2AWYRAM3/events.json","paper":"https://pith.science/paper/NB5FUT3S"},"agent_actions":{"view_html":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3","download_json":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3.json","view_paper":"https://pith.science/paper/NB5FUT3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14585&json=true","fetch_graph":"https://pith.science/api/pith-number/NB5FUT3SX7MEHLHVGR2AWYRAM3/graph.json","fetch_events":"https://pith.science/api/pith-number/NB5FUT3SX7MEHLHVGR2AWYRAM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3/action/storage_attestation","attest_author":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3/action/author_attestation","sign_citation":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3/action/citation_signature","submit_replication":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3/action/replication_record"}},"created_at":"2026-07-05T10:15:19.023428+00:00","updated_at":"2026-07-05T10:15:19.023428+00:00"}