{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GTYDMSS7HAIWRXMK6GZMNBQXM4","short_pith_number":"pith:GTYDMSS7","canonical_record":{"source":{"id":"2112.07423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T14:14:17Z","cross_cats_sorted":[],"title_canon_sha256":"d2e88cb1219a9230319bdc6038668eebb5dae278b587695c0f3e4eb5ed9ca860","abstract_canon_sha256":"c46c6e49c4f98bdda9e251666db267e90f158419b0cf7b3464327b5f59718f92"},"schema_version":"1.0"},"canonical_sha256":"34f0364a5f381168dd8af1b2c6861767373f39385a1c28202efd372f9b52c4e0","source":{"kind":"arxiv","id":"2112.07423","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07423","created_at":"2026-07-05T03:40:57Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07423v1","created_at":"2026-07-05T03:40:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07423","created_at":"2026-07-05T03:40:57Z"},{"alias_kind":"pith_short_12","alias_value":"GTYDMSS7HAIW","created_at":"2026-07-05T03:40:57Z"},{"alias_kind":"pith_short_16","alias_value":"GTYDMSS7HAIWRXMK","created_at":"2026-07-05T03:40:57Z"},{"alias_kind":"pith_short_8","alias_value":"GTYDMSS7","created_at":"2026-07-05T03:40:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GTYDMSS7HAIWRXMK6GZMNBQXM4","target":"record","payload":{"canonical_record":{"source":{"id":"2112.07423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T14:14:17Z","cross_cats_sorted":[],"title_canon_sha256":"d2e88cb1219a9230319bdc6038668eebb5dae278b587695c0f3e4eb5ed9ca860","abstract_canon_sha256":"c46c6e49c4f98bdda9e251666db267e90f158419b0cf7b3464327b5f59718f92"},"schema_version":"1.0"},"canonical_sha256":"34f0364a5f381168dd8af1b2c6861767373f39385a1c28202efd372f9b52c4e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:57.979520Z","signature_b64":"JD+ZWDP8voHM+k1WSjpgdL5t9WBKa0OlNaqrmVdnonr6PNXV6+KInnxVlSsL3DJeCLF/Jm9DZRHra7aKyCtTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34f0364a5f381168dd8af1b2c6861767373f39385a1c28202efd372f9b52c4e0","last_reissued_at":"2026-07-05T03:40:57.979035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:57.979035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.07423","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":"2026-07-05T03:40:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rNbF6V+VaEuqituI6olE6Q7890XivJ7wiW5U59LV180GyeOuQx7k0VBBDPKWynSWOk4x/k/efA2N3A2EXfmuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:10:41.540066Z"},"content_sha256":"1692f19e54f276ab45a7b52a7d68d5e1012aaf82738c6fbe1ff88672246583da","schema_version":"1.0","event_id":"sha256:1692f19e54f276ab45a7b52a7d68d5e1012aaf82738c6fbe1ff88672246583da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GTYDMSS7HAIWRXMK6GZMNBQXM4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Modal Perception Attention Network with Self-Supervised Learning for Audio-Visual Speaker Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tang, Hong Liu, Yidi Li","submitted_at":"2021-12-14T14:14:17Z","abstract_excerpt":"Multi-modal fusion is proven to be an effective method to improve the accuracy and robustness of speaker tracking, especially in complex scenarios. However, how to combine the heterogeneous information and exploit the complementarity of multi-modal signals remains a challenging issue. In this paper, we propose a novel Multi-modal Perception Tracker (MPT) for speaker tracking using both audio and visual modalities. Specifically, a novel acoustic map based on spatial-temporal Global Coherence Field (stGCF) is first constructed for heterogeneous signal fusion, which employs a camera model to map "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07423","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/2112.07423/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":"2026-07-05T03:40:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hk8hda09Nounfmz1J6epUmAp7CF3485p6bcx5aNxe+zZOG0dRN/RbFRDU3+Q8fAypqc96gYslaWaG6ID4LAvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:10:41.540453Z"},"content_sha256":"39dd73505fcb7b9eb6fe4de4d08a3b5794bfffcc5c2ad7041fd3b508b96b2de2","schema_version":"1.0","event_id":"sha256:39dd73505fcb7b9eb6fe4de4d08a3b5794bfffcc5c2ad7041fd3b508b96b2de2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTYDMSS7HAIWRXMK6GZMNBQXM4/bundle.json","state_url":"https://pith.science/pith/GTYDMSS7HAIWRXMK6GZMNBQXM4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTYDMSS7HAIWRXMK6GZMNBQXM4/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":"2026-07-06T11:10:41Z","links":{"resolver":"https://pith.science/pith/GTYDMSS7HAIWRXMK6GZMNBQXM4","bundle":"https://pith.science/pith/GTYDMSS7HAIWRXMK6GZMNBQXM4/bundle.json","state":"https://pith.science/pith/GTYDMSS7HAIWRXMK6GZMNBQXM4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTYDMSS7HAIWRXMK6GZMNBQXM4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GTYDMSS7HAIWRXMK6GZMNBQXM4","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":"c46c6e49c4f98bdda9e251666db267e90f158419b0cf7b3464327b5f59718f92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T14:14:17Z","title_canon_sha256":"d2e88cb1219a9230319bdc6038668eebb5dae278b587695c0f3e4eb5ed9ca860"},"schema_version":"1.0","source":{"id":"2112.07423","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07423","created_at":"2026-07-05T03:40:57Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07423v1","created_at":"2026-07-05T03:40:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07423","created_at":"2026-07-05T03:40:57Z"},{"alias_kind":"pith_short_12","alias_value":"GTYDMSS7HAIW","created_at":"2026-07-05T03:40:57Z"},{"alias_kind":"pith_short_16","alias_value":"GTYDMSS7HAIWRXMK","created_at":"2026-07-05T03:40:57Z"},{"alias_kind":"pith_short_8","alias_value":"GTYDMSS7","created_at":"2026-07-05T03:40:57Z"}],"graph_snapshots":[{"event_id":"sha256:39dd73505fcb7b9eb6fe4de4d08a3b5794bfffcc5c2ad7041fd3b508b96b2de2","target":"graph","created_at":"2026-07-05T03:40:57Z","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/2112.07423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal fusion is proven to be an effective method to improve the accuracy and robustness of speaker tracking, especially in complex scenarios. However, how to combine the heterogeneous information and exploit the complementarity of multi-modal signals remains a challenging issue. In this paper, we propose a novel Multi-modal Perception Tracker (MPT) for speaker tracking using both audio and visual modalities. Specifically, a novel acoustic map based on spatial-temporal Global Coherence Field (stGCF) is first constructed for heterogeneous signal fusion, which employs a camera model to map ","authors_text":"Hao Tang, Hong Liu, Yidi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T14:14:17Z","title":"Multi-Modal Perception Attention Network with Self-Supervised Learning for Audio-Visual Speaker Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07423","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":"sha256:1692f19e54f276ab45a7b52a7d68d5e1012aaf82738c6fbe1ff88672246583da","target":"record","created_at":"2026-07-05T03:40:57Z","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":"c46c6e49c4f98bdda9e251666db267e90f158419b0cf7b3464327b5f59718f92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T14:14:17Z","title_canon_sha256":"d2e88cb1219a9230319bdc6038668eebb5dae278b587695c0f3e4eb5ed9ca860"},"schema_version":"1.0","source":{"id":"2112.07423","kind":"arxiv","version":1}},"canonical_sha256":"34f0364a5f381168dd8af1b2c6861767373f39385a1c28202efd372f9b52c4e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34f0364a5f381168dd8af1b2c6861767373f39385a1c28202efd372f9b52c4e0","first_computed_at":"2026-07-05T03:40:57.979035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:57.979035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JD+ZWDP8voHM+k1WSjpgdL5t9WBKa0OlNaqrmVdnonr6PNXV6+KInnxVlSsL3DJeCLF/Jm9DZRHra7aKyCtTCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:57.979520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07423","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1692f19e54f276ab45a7b52a7d68d5e1012aaf82738c6fbe1ff88672246583da","sha256:39dd73505fcb7b9eb6fe4de4d08a3b5794bfffcc5c2ad7041fd3b508b96b2de2"],"state_sha256":"e240e25facef3f86746535d4654ff63026875f19ee3fba87ed996faec8858bc1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2YGyY77m16eb6wjCLfouvAOdX+U2CV5OgLFlduFDR2lb+KsZGf9LmB16+0Ecp3UPixBArAXRuJsv72n36QotBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T11:10:41.542398Z","bundle_sha256":"1d84a01310cb56e89238da242d5e15ab84313e727edd2865d21902d2b6de7eca"}}