{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T7NU52WX6P6CKGQSJJKIJNXP62","short_pith_number":"pith:T7NU52WX","canonical_record":{"source":{"id":"2412.15691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T09:10:17Z","cross_cats_sorted":[],"title_canon_sha256":"c7ddcfa862ce998968ab59be31035c32274ac09dc983c92c3c03e0f0990c2ffd","abstract_canon_sha256":"dfab457f8e13d46365ce3b074952a374fb218266320ca97d780183a7412b91de"},"schema_version":"1.0"},"canonical_sha256":"9fdb4eead7f3fc251a124a5484b6eff6a9579372ddc70ab3dae5276f034af023","source":{"kind":"arxiv","id":"2412.15691","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15691","created_at":"2026-07-05T09:52:28Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15691v1","created_at":"2026-07-05T09:52:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15691","created_at":"2026-07-05T09:52:28Z"},{"alias_kind":"pith_short_12","alias_value":"T7NU52WX6P6C","created_at":"2026-07-05T09:52:28Z"},{"alias_kind":"pith_short_16","alias_value":"T7NU52WX6P6CKGQS","created_at":"2026-07-05T09:52:28Z"},{"alias_kind":"pith_short_8","alias_value":"T7NU52WX","created_at":"2026-07-05T09:52:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T7NU52WX6P6CKGQSJJKIJNXP62","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T09:10:17Z","cross_cats_sorted":[],"title_canon_sha256":"c7ddcfa862ce998968ab59be31035c32274ac09dc983c92c3c03e0f0990c2ffd","abstract_canon_sha256":"dfab457f8e13d46365ce3b074952a374fb218266320ca97d780183a7412b91de"},"schema_version":"1.0"},"canonical_sha256":"9fdb4eead7f3fc251a124a5484b6eff6a9579372ddc70ab3dae5276f034af023","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:28.465328Z","signature_b64":"K+qDIsONpDGCBCYlanPdsCMnLFJztbWTmRvAazSeefgxD3e5wJvq+LfFvkwcVYj/DGfJVVj2pHUDcrBa3Ic/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fdb4eead7f3fc251a124a5484b6eff6a9579372ddc70ab3dae5276f034af023","last_reissued_at":"2026-07-05T09:52:28.464881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:28.464881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15691","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":"2026-07-05T09:52:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sLUYLJR/F8/AMTcO2VngdK15q3t8F3vLVo01Uej6+Np7SBbw4icVwOVVH9XpyjFZ3jPw+EN46M0kL3riGFEdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:19:23.730746Z"},"content_sha256":"2bc76c882e5ae480e896fbd4312e9394c44a01f9068edb9de429d49d591a5b99","schema_version":"1.0","event_id":"sha256:2bc76c882e5ae480e896fbd4312e9394c44a01f9068edb9de429d49d591a5b99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T7NU52WX6P6CKGQSJJKIJNXP62","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bineng Zhong, Chen Zhao, Jian Yang, Jun Li, Xiantao Hu, Xu Zhao, Ying Tai, Zhenyu Zhang","submitted_at":"2024-12-20T09:10:17Z","abstract_excerpt":"Multimodal tracking has garnered widespread attention as a result of its ability to effectively address the inherent limitations of traditional RGB tracking. However, existing multimodal trackers mainly focus on the fusion and enhancement of spatial features or merely leverage the sparse temporal relationships between video frames. These approaches do not fully exploit the temporal correlations in multimodal videos, making it difficult to capture the dynamic changes and motion information of targets in complex scenarios. To alleviate this problem, we propose a unified multimodal spatial-tempor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15691","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/2412.15691/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":"2026-07-05T09:52:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0yJWV95nMLqdwy59+xTN4z7CtXXdKbSiNqFA6FX5Z917oPQNOnvb93XaPWtoBDlS+X5ieg/zD0re50k4PPA3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:19:23.731239Z"},"content_sha256":"dc82fa6222743993b34758e555a4a03b07528ea080c5b7b664814a95bbd52c59","schema_version":"1.0","event_id":"sha256:dc82fa6222743993b34758e555a4a03b07528ea080c5b7b664814a95bbd52c59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T7NU52WX6P6CKGQSJJKIJNXP62/bundle.json","state_url":"https://pith.science/pith/T7NU52WX6P6CKGQSJJKIJNXP62/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T7NU52WX6P6CKGQSJJKIJNXP62/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":"2026-08-21T03:19:23Z","links":{"resolver":"https://pith.science/pith/T7NU52WX6P6CKGQSJJKIJNXP62","bundle":"https://pith.science/pith/T7NU52WX6P6CKGQSJJKIJNXP62/bundle.json","state":"https://pith.science/pith/T7NU52WX6P6CKGQSJJKIJNXP62/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T7NU52WX6P6CKGQSJJKIJNXP62/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T7NU52WX6P6CKGQSJJKIJNXP62","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":"dfab457f8e13d46365ce3b074952a374fb218266320ca97d780183a7412b91de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T09:10:17Z","title_canon_sha256":"c7ddcfa862ce998968ab59be31035c32274ac09dc983c92c3c03e0f0990c2ffd"},"schema_version":"1.0","source":{"id":"2412.15691","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15691","created_at":"2026-07-05T09:52:28Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15691v1","created_at":"2026-07-05T09:52:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15691","created_at":"2026-07-05T09:52:28Z"},{"alias_kind":"pith_short_12","alias_value":"T7NU52WX6P6C","created_at":"2026-07-05T09:52:28Z"},{"alias_kind":"pith_short_16","alias_value":"T7NU52WX6P6CKGQS","created_at":"2026-07-05T09:52:28Z"},{"alias_kind":"pith_short_8","alias_value":"T7NU52WX","created_at":"2026-07-05T09:52:28Z"}],"graph_snapshots":[{"event_id":"sha256:dc82fa6222743993b34758e555a4a03b07528ea080c5b7b664814a95bbd52c59","target":"graph","created_at":"2026-07-05T09:52:28Z","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/2412.15691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal tracking has garnered widespread attention as a result of its ability to effectively address the inherent limitations of traditional RGB tracking. However, existing multimodal trackers mainly focus on the fusion and enhancement of spatial features or merely leverage the sparse temporal relationships between video frames. These approaches do not fully exploit the temporal correlations in multimodal videos, making it difficult to capture the dynamic changes and motion information of targets in complex scenarios. To alleviate this problem, we propose a unified multimodal spatial-tempor","authors_text":"Bineng Zhong, Chen Zhao, Jian Yang, Jun Li, Xiantao Hu, Xu Zhao, Ying Tai, Zhenyu Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T09:10:17Z","title":"Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15691","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":"sha256:2bc76c882e5ae480e896fbd4312e9394c44a01f9068edb9de429d49d591a5b99","target":"record","created_at":"2026-07-05T09:52:28Z","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":"dfab457f8e13d46365ce3b074952a374fb218266320ca97d780183a7412b91de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T09:10:17Z","title_canon_sha256":"c7ddcfa862ce998968ab59be31035c32274ac09dc983c92c3c03e0f0990c2ffd"},"schema_version":"1.0","source":{"id":"2412.15691","kind":"arxiv","version":1}},"canonical_sha256":"9fdb4eead7f3fc251a124a5484b6eff6a9579372ddc70ab3dae5276f034af023","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fdb4eead7f3fc251a124a5484b6eff6a9579372ddc70ab3dae5276f034af023","first_computed_at":"2026-07-05T09:52:28.464881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:28.464881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K+qDIsONpDGCBCYlanPdsCMnLFJztbWTmRvAazSeefgxD3e5wJvq+LfFvkwcVYj/DGfJVVj2pHUDcrBa3Ic/AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:28.465328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15691","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bc76c882e5ae480e896fbd4312e9394c44a01f9068edb9de429d49d591a5b99","sha256:dc82fa6222743993b34758e555a4a03b07528ea080c5b7b664814a95bbd52c59"],"state_sha256":"8139447b821aacbd5139a64d8e0abe9cb875c44ceaf7131c5f9009815d8a7dc7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E78k93ulNVfBeNAt16TsNQitYZvWv8ZUU3j5G/Q/RTtKbfEOgGKY421Y5uchmqPtrdDgldHtex8nLrJw/i5MBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T03:19:23.736248Z","bundle_sha256":"8e33a9724116c47bc066ed9d20f78a84f7828cb734a6f20778e2c60009ea4158"}}