{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MKEHJDR5AWAOUEK5N2RKBNZGNA","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":"8c0240bb382defbcb15906753e0905ed0ed62cc2f80afcf8670036c30f5fa3ef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T05:58:10Z","title_canon_sha256":"bdf32a40a421849abcfb45077384a4060f7bebfc9d02cd23c7a2dfb11bac1f7d"},"schema_version":"1.0","source":{"id":"2405.14200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14200","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14200v2","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14200","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"pith_short_12","alias_value":"MKEHJDR5AWAO","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"pith_short_16","alias_value":"MKEHJDR5AWAOUEK5","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"pith_short_8","alias_value":"MKEHJDR5","created_at":"2026-07-05T08:25:34Z"}],"graph_snapshots":[{"event_id":"sha256:96ddbf8a61530f75f6a4699231197fc570184d2489864aa271fb1f94ee81a7da","target":"graph","created_at":"2026-07-05T08:25:34Z","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/2405.14200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal object tracking (MMOT) is an emerging field that combines data from various modalities, \\eg vision (RGB), depth, thermal infrared, event, language and audio, to estimate the state of an arbitrary object in a video sequence. It is of great significance for many applications such as autonomous driving and intelligent surveillance. In recent years, MMOT has received more and more attention. However, existing MMOT algorithms mainly focus on two modalities (\\eg RGB+depth, RGB+thermal infrared, and RGB+language). To leverage more modalities, some recent efforts have been made to learn a ","authors_text":"Chunhui Zhang, Hao Wen, Li Liu, Xi Zhou, Yanfeng Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T05:58:10Z","title":"Awesome Multi-modal Object Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14200","kind":"arxiv","version":2},"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":"sha256:6f769e3f55f392c5772ea5c862df257188cddeff27447748c7d929fd3dc1c64a","target":"record","created_at":"2026-07-05T08:25:34Z","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":"8c0240bb382defbcb15906753e0905ed0ed62cc2f80afcf8670036c30f5fa3ef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T05:58:10Z","title_canon_sha256":"bdf32a40a421849abcfb45077384a4060f7bebfc9d02cd23c7a2dfb11bac1f7d"},"schema_version":"1.0","source":{"id":"2405.14200","kind":"arxiv","version":2}},"canonical_sha256":"6288748e3d0580ea115d6ea2a0b72668099330c7b7a9d459530a5e06181ee1e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6288748e3d0580ea115d6ea2a0b72668099330c7b7a9d459530a5e06181ee1e2","first_computed_at":"2026-07-05T08:25:34.487567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:34.487567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dPkfwK1U0MENpZkP85wY8CuaHBa8s9KAB6SRJWY42MhtqUBDm3IEnONU17jI6smnE49EReKQvxvso4WQK1aFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:34.487992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f769e3f55f392c5772ea5c862df257188cddeff27447748c7d929fd3dc1c64a","sha256:96ddbf8a61530f75f6a4699231197fc570184d2489864aa271fb1f94ee81a7da"],"state_sha256":"615dbd9b102d4458a0f9bbc3967c6c885c75338f25c44d36f75eb598d87536aa"}