{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NEDWPNDAIXJ5736WLMJQZ6XMVT","short_pith_number":"pith:NEDWPNDA","canonical_record":{"source":{"id":"2410.05964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T12:15:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77109a2274f0daae27b54a83a469e0ae5371266f173fb76f144bcc62f2ad0d83","abstract_canon_sha256":"be6dbc07e65ad4d24cc56106a8b04a77c56149be18302977a788f9d9842ef689"},"schema_version":"1.0"},"canonical_sha256":"690767b46045d3dfefd65b130cfaecacf89904b1e4e512ed1338f1c728674d79","source":{"kind":"arxiv","id":"2410.05964","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05964","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05964v1","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05964","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_12","alias_value":"NEDWPNDAIXJ5","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_16","alias_value":"NEDWPNDAIXJ5736W","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_8","alias_value":"NEDWPNDA","created_at":"2026-07-05T09:17:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NEDWPNDAIXJ5736WLMJQZ6XMVT","target":"record","payload":{"canonical_record":{"source":{"id":"2410.05964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T12:15:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77109a2274f0daae27b54a83a469e0ae5371266f173fb76f144bcc62f2ad0d83","abstract_canon_sha256":"be6dbc07e65ad4d24cc56106a8b04a77c56149be18302977a788f9d9842ef689"},"schema_version":"1.0"},"canonical_sha256":"690767b46045d3dfefd65b130cfaecacf89904b1e4e512ed1338f1c728674d79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:53.821607Z","signature_b64":"9skogM4wlPUlFIJbHbuwMJ0oHDOLywWtKggKoaa7XTjHaiNlUsyUuFBgS2iH13RXuhpNUqmUDpICn4FMDHRrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"690767b46045d3dfefd65b130cfaecacf89904b1e4e512ed1338f1c728674d79","last_reissued_at":"2026-07-05T09:17:53.821152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:53.821152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.05964","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IbGkgYISJTzFmpzSx3wbFyRVXu9cIc7ihdZFba5mZSGaI8a8GkYsA/aR7+PUu/17+HdISul9mV/UIxoHf3P6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:31:25.775636Z"},"content_sha256":"6ebd23830477d19fa416bd412ad35b34666a493cac11df953c6568361cdff81f","schema_version":"1.0","event_id":"sha256:6ebd23830477d19fa416bd412ad35b34666a493cac11df953c6568361cdff81f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NEDWPNDAIXJ5736WLMJQZ6XMVT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bing Yang, Hong Liu, Yidi Li","submitted_at":"2024-10-08T12:15:17Z","abstract_excerpt":"Audio-visual speaker tracking aims to determine the location of human targets in a scene using signals captured by a multi-sensor platform, whose accuracy and robustness can be improved by multi-modal fusion methods. Recently, several fusion methods have been proposed to model the correlation in multiple modalities. However, for the speaker tracking problem, the cross-modal interaction between audio and visual signals hasn't been well exploited. To this end, we present a novel Speaker Tracking Network (STNet) with a deep audio-visual fusion model in this work. We design a visual-guided acousti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05964","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/2410.05964/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EdXGJKrAVKDPxy3gcnXPIp2DSSSfogDHCybwiPLuRYSj2aQPNe4FTOgFAg+3o64GKY2qgfZZUrgaNblbTC7jCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:31:25.776032Z"},"content_sha256":"3cac720a5f9fd0fd0b8804a6e1f93e05bd3e0fc6e02fbb0a76c0b23959888571","schema_version":"1.0","event_id":"sha256:3cac720a5f9fd0fd0b8804a6e1f93e05bd3e0fc6e02fbb0a76c0b23959888571"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NEDWPNDAIXJ5736WLMJQZ6XMVT/bundle.json","state_url":"https://pith.science/pith/NEDWPNDAIXJ5736WLMJQZ6XMVT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NEDWPNDAIXJ5736WLMJQZ6XMVT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T13:31:25Z","links":{"resolver":"https://pith.science/pith/NEDWPNDAIXJ5736WLMJQZ6XMVT","bundle":"https://pith.science/pith/NEDWPNDAIXJ5736WLMJQZ6XMVT/bundle.json","state":"https://pith.science/pith/NEDWPNDAIXJ5736WLMJQZ6XMVT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NEDWPNDAIXJ5736WLMJQZ6XMVT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NEDWPNDAIXJ5736WLMJQZ6XMVT","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":"be6dbc07e65ad4d24cc56106a8b04a77c56149be18302977a788f9d9842ef689","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T12:15:17Z","title_canon_sha256":"77109a2274f0daae27b54a83a469e0ae5371266f173fb76f144bcc62f2ad0d83"},"schema_version":"1.0","source":{"id":"2410.05964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05964","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05964v1","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05964","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_12","alias_value":"NEDWPNDAIXJ5","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_16","alias_value":"NEDWPNDAIXJ5736W","created_at":"2026-07-05T09:17:53Z"},{"alias_kind":"pith_short_8","alias_value":"NEDWPNDA","created_at":"2026-07-05T09:17:53Z"}],"graph_snapshots":[{"event_id":"sha256:3cac720a5f9fd0fd0b8804a6e1f93e05bd3e0fc6e02fbb0a76c0b23959888571","target":"graph","created_at":"2026-07-05T09:17:53Z","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/2410.05964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual speaker tracking aims to determine the location of human targets in a scene using signals captured by a multi-sensor platform, whose accuracy and robustness can be improved by multi-modal fusion methods. Recently, several fusion methods have been proposed to model the correlation in multiple modalities. However, for the speaker tracking problem, the cross-modal interaction between audio and visual signals hasn't been well exploited. To this end, we present a novel Speaker Tracking Network (STNet) with a deep audio-visual fusion model in this work. We design a visual-guided acousti","authors_text":"Bing Yang, Hong Liu, Yidi Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T12:15:17Z","title":"STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05964","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":"sha256:6ebd23830477d19fa416bd412ad35b34666a493cac11df953c6568361cdff81f","target":"record","created_at":"2026-07-05T09:17:53Z","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":"be6dbc07e65ad4d24cc56106a8b04a77c56149be18302977a788f9d9842ef689","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T12:15:17Z","title_canon_sha256":"77109a2274f0daae27b54a83a469e0ae5371266f173fb76f144bcc62f2ad0d83"},"schema_version":"1.0","source":{"id":"2410.05964","kind":"arxiv","version":1}},"canonical_sha256":"690767b46045d3dfefd65b130cfaecacf89904b1e4e512ed1338f1c728674d79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"690767b46045d3dfefd65b130cfaecacf89904b1e4e512ed1338f1c728674d79","first_computed_at":"2026-07-05T09:17:53.821152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:53.821152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9skogM4wlPUlFIJbHbuwMJ0oHDOLywWtKggKoaa7XTjHaiNlUsyUuFBgS2iH13RXuhpNUqmUDpICn4FMDHRrDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:53.821607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ebd23830477d19fa416bd412ad35b34666a493cac11df953c6568361cdff81f","sha256:3cac720a5f9fd0fd0b8804a6e1f93e05bd3e0fc6e02fbb0a76c0b23959888571"],"state_sha256":"64ce59c47a86ed81df4f9f7866a000859e5d811817a642d20b0ac94d4a52a471"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ndGxaKe5T10DWnNgkQ5/Te4Npz/D1wTR6BiG4G3wVx9VPcSpKd5FpLWAtRcnvRl4y1/gIaidBMJyDTGvctxAAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:31:25.777991Z","bundle_sha256":"8fef9343e3fbefdf2756fc6004769fbb4fd43f8a9c3c964d0a54c0fc94482021"}}