{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4CYFNVI4TFXB35SZPQAFGIH5RT","short_pith_number":"pith:4CYFNVI4","schema_version":"1.0","canonical_sha256":"e0b056d51c996e1df6597c005320fd8cf3aec83d58e7b257bbe65c2a39b5cb30","source":{"kind":"arxiv","id":"2503.06621","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Updates for Language Adaptation in Visual-Language Tracking","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bineng Zhong, Jian Nong, Qihua Liang, Shuxiang Song, Xiaohai Li, Zhiyi Mo","submitted_at":"2025-03-09T13:47:19Z","abstract_excerpt":"The consistency between the semantic information provided by the multi-modal reference and the tracked object is crucial for visual-language (VL) tracking. However, existing VL tracking frameworks rely on static multi-modal references to locate dynamic objects, which can lead to semantic discrepancies and reduce the robustness of the tracker. To address this issue, we propose a novel vision-language tracking framework, named DUTrack, which captures the latest state of the target by dynamically updating multi-modal references to maintain consistency. Specifically, we introduce a Dynamic Languag"},"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":"2503.06621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T13:47:19Z","cross_cats_sorted":[],"title_canon_sha256":"cb5b3e987d022cb99723defdab15fb951ef81f5d9993a4c57d874c62c9374556","abstract_canon_sha256":"b06fc241edc7e014c332d4e431da571b3e6d7adbb39be216fb4e864bfad0f678"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:38.438108Z","signature_b64":"a4SwavWgPxlHEC5J5o38b6EUAA2TWnhR9jWMx8Fjs2dS7eFw2dW5L3D2uAvfPV3zq2zSz6oldHE4Fuhr8zENAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0b056d51c996e1df6597c005320fd8cf3aec83d58e7b257bbe65c2a39b5cb30","last_reissued_at":"2026-07-05T10:27:38.437500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:38.437500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Updates for Language Adaptation in Visual-Language Tracking","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bineng Zhong, Jian Nong, Qihua Liang, Shuxiang Song, Xiaohai Li, Zhiyi Mo","submitted_at":"2025-03-09T13:47:19Z","abstract_excerpt":"The consistency between the semantic information provided by the multi-modal reference and the tracked object is crucial for visual-language (VL) tracking. However, existing VL tracking frameworks rely on static multi-modal references to locate dynamic objects, which can lead to semantic discrepancies and reduce the robustness of the tracker. To address this issue, we propose a novel vision-language tracking framework, named DUTrack, which captures the latest state of the target by dynamically updating multi-modal references to maintain consistency. Specifically, we introduce a Dynamic Languag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06621","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/2503.06621/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":"2503.06621","created_at":"2026-07-05T10:27:38.437560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06621v1","created_at":"2026-07-05T10:27:38.437560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06621","created_at":"2026-07-05T10:27:38.437560+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CYFNVI4TFXB","created_at":"2026-07-05T10:27:38.437560+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CYFNVI4TFXB35SZ","created_at":"2026-07-05T10:27:38.437560+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CYFNVI4","created_at":"2026-07-05T10:27:38.437560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29357","citing_title":"Dynamic Parsing and Updating Natural Language Specification using VLMs for Robust Vision-Language Tracking","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CYFNVI4TFXB35SZPQAFGIH5RT","json":"https://pith.science/pith/4CYFNVI4TFXB35SZPQAFGIH5RT.json","graph_json":"https://pith.science/api/pith-number/4CYFNVI4TFXB35SZPQAFGIH5RT/graph.json","events_json":"https://pith.science/api/pith-number/4CYFNVI4TFXB35SZPQAFGIH5RT/events.json","paper":"https://pith.science/paper/4CYFNVI4"},"agent_actions":{"view_html":"https://pith.science/pith/4CYFNVI4TFXB35SZPQAFGIH5RT","download_json":"https://pith.science/pith/4CYFNVI4TFXB35SZPQAFGIH5RT.json","view_paper":"https://pith.science/paper/4CYFNVI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06621&json=true","fetch_graph":"https://pith.science/api/pith-number/4CYFNVI4TFXB35SZPQAFGIH5RT/graph.json","fetch_events":"https://pith.science/api/pith-number/4CYFNVI4TFXB35SZPQAFGIH5RT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CYFNVI4TFXB35SZPQAFGIH5RT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CYFNVI4TFXB35SZPQAFGIH5RT/action/storage_attestation","attest_author":"https://pith.science/pith/4CYFNVI4TFXB35SZPQAFGIH5RT/action/author_attestation","sign_citation":"https://pith.science/pith/4CYFNVI4TFXB35SZPQAFGIH5RT/action/citation_signature","submit_replication":"https://pith.science/pith/4CYFNVI4TFXB35SZPQAFGIH5RT/action/replication_record"}},"created_at":"2026-07-05T10:27:38.437560+00:00","updated_at":"2026-07-05T10:27:38.437560+00:00"}