{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YBK54A3S7RSXIZ5U6I63MMMVKI","short_pith_number":"pith:YBK54A3S","schema_version":"1.0","canonical_sha256":"c055de0372fc657467b4f23db6319552245e0b696d102f58d6f9013f7be1873c","source":{"kind":"arxiv","id":"2507.20177","version":1},"attestation_state":"computed","paper":{"title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bineng Zhong, Guorong Li, Qihua Liang, Rongrong Ji, Shengping Zhang, Xianxian Li, Yaozong Zheng","submitted_at":"2025-07-27T08:47:42Z","abstract_excerpt":"We propose a universal video-level modality-awareness tracking model with online dense temporal token learning (called {\\modaltracker}). It is designed to support various tracking tasks, including RGB, RGB+Thermal, RGB+Depth, and RGB+Event, utilizing the same model architecture and parameters. Specifically, our model is designed with three core goals: \\textbf{Video-level Sampling}. We expand the model's inputs to a video sequence level, aiming to see a richer video context from an near-global perspective. \\textbf{Video-level Association}. Furthermore, we introduce two simple yet effective onli"},"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":"2507.20177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T08:47:42Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"77277abe4a8dce453b1d06e3bc810fa40eac771dcd9e169db10feda186b8ee18","abstract_canon_sha256":"2422b3a643c46b1e791c5baf848ffe19f873d76dd8378dc1e86c4f6b3d62150d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:53.418817Z","signature_b64":"B9tS1dJuUUjg7PVBMlvmONBuaFPJZNhEx9hu9Uq0dzVHh1UH85Ldm8Mulix5v9POpGJhsUVQDX5pZKhhsXPwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c055de0372fc657467b4f23db6319552245e0b696d102f58d6f9013f7be1873c","last_reissued_at":"2026-07-05T11:44:53.418392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:53.418392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bineng Zhong, Guorong Li, Qihua Liang, Rongrong Ji, Shengping Zhang, Xianxian Li, Yaozong Zheng","submitted_at":"2025-07-27T08:47:42Z","abstract_excerpt":"We propose a universal video-level modality-awareness tracking model with online dense temporal token learning (called {\\modaltracker}). It is designed to support various tracking tasks, including RGB, RGB+Thermal, RGB+Depth, and RGB+Event, utilizing the same model architecture and parameters. Specifically, our model is designed with three core goals: \\textbf{Video-level Sampling}. We expand the model's inputs to a video sequence level, aiming to see a richer video context from an near-global perspective. \\textbf{Video-level Association}. Furthermore, we introduce two simple yet effective onli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20177","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/2507.20177/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":"2507.20177","created_at":"2026-07-05T11:44:53.418454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20177v1","created_at":"2026-07-05T11:44:53.418454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20177","created_at":"2026-07-05T11:44:53.418454+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBK54A3S7RSX","created_at":"2026-07-05T11:44:53.418454+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBK54A3S7RSXIZ5U","created_at":"2026-07-05T11:44:53.418454+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBK54A3S","created_at":"2026-07-05T11:44:53.418454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01602","citing_title":"Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment","ref_index":160,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI","json":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI.json","graph_json":"https://pith.science/api/pith-number/YBK54A3S7RSXIZ5U6I63MMMVKI/graph.json","events_json":"https://pith.science/api/pith-number/YBK54A3S7RSXIZ5U6I63MMMVKI/events.json","paper":"https://pith.science/paper/YBK54A3S"},"agent_actions":{"view_html":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI","download_json":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI.json","view_paper":"https://pith.science/paper/YBK54A3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20177&json=true","fetch_graph":"https://pith.science/api/pith-number/YBK54A3S7RSXIZ5U6I63MMMVKI/graph.json","fetch_events":"https://pith.science/api/pith-number/YBK54A3S7RSXIZ5U6I63MMMVKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI/action/storage_attestation","attest_author":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI/action/author_attestation","sign_citation":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI/action/citation_signature","submit_replication":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI/action/replication_record"}},"created_at":"2026-07-05T11:44:53.418454+00:00","updated_at":"2026-07-05T11:44:53.418454+00:00"}