{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R7TXB266AEIG6BUD2OEV2G3U4P","short_pith_number":"pith:R7TXB266","schema_version":"1.0","canonical_sha256":"8fe770ebde01106f0683d3895d1b74e3c149fe298d732dd6693d9b9c269463b3","source":{"kind":"arxiv","id":"2403.16002","version":2},"attestation_state":"computed","paper":{"title":"SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiazheng Xing, Junhao Chen, Kai Tang, Liang Liu, Mengmeng Wang, Shuo Xin, Xiaojun Hou, Yaowei Guo, Yijie Qian, Yong Liu, Zhengkai Jiang","submitted_at":"2024-03-24T04:15:50Z","abstract_excerpt":"Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness. Early research focused on fully fine-tuning RGB-based trackers, which was inefficient and lacked generalized representation due to the scarcity of multimodal data. Therefore, recent studies have utilized prompt tuning to transfer pre-trained RGB-based trackers to multimodal data. However, the modality gap limits pre-trained knowledge recall, and the dominance of the RGB modality persists, preventing the full utilization of information from other modalities. To address these issues, we propo"},"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":"2403.16002","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-24T04:15:50Z","cross_cats_sorted":[],"title_canon_sha256":"91d395fe288808eaa725ce8d32bee3f10aeac51465dcaf550929a60c9ae0ce72","abstract_canon_sha256":"34b5b3461a078f94a7d4647af63fe2388d43d40519aad1f8bf7f72232359db8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:39.165897Z","signature_b64":"C+pMCGSppjaiwi+p20jrC6daj2OntZ4YHhh5me0kDvUMaaVQqEYpPM2+28VXLbgrIyEC0z0O1e81OY7wM+T4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fe770ebde01106f0683d3895d1b74e3c149fe298d732dd6693d9b9c269463b3","last_reissued_at":"2026-07-05T08:01:39.165359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:39.165359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiazheng Xing, Junhao Chen, Kai Tang, Liang Liu, Mengmeng Wang, Shuo Xin, Xiaojun Hou, Yaowei Guo, Yijie Qian, Yong Liu, Zhengkai Jiang","submitted_at":"2024-03-24T04:15:50Z","abstract_excerpt":"Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness. Early research focused on fully fine-tuning RGB-based trackers, which was inefficient and lacked generalized representation due to the scarcity of multimodal data. Therefore, recent studies have utilized prompt tuning to transfer pre-trained RGB-based trackers to multimodal data. However, the modality gap limits pre-trained knowledge recall, and the dominance of the RGB modality persists, preventing the full utilization of information from other modalities. To address these issues, we propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16002","kind":"arxiv","version":2},"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/2403.16002/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":"2403.16002","created_at":"2026-07-05T08:01:39.165429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16002v2","created_at":"2026-07-05T08:01:39.165429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16002","created_at":"2026-07-05T08:01:39.165429+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7TXB266AEIG","created_at":"2026-07-05T08:01:39.165429+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7TXB266AEIG6BUD","created_at":"2026-07-05T08:01:39.165429+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7TXB266","created_at":"2026-07-05T08:01:39.165429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06583","citing_title":"Adaptive Perception for Unified Visual Multi-modal Object Tracking","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R7TXB266AEIG6BUD2OEV2G3U4P","json":"https://pith.science/pith/R7TXB266AEIG6BUD2OEV2G3U4P.json","graph_json":"https://pith.science/api/pith-number/R7TXB266AEIG6BUD2OEV2G3U4P/graph.json","events_json":"https://pith.science/api/pith-number/R7TXB266AEIG6BUD2OEV2G3U4P/events.json","paper":"https://pith.science/paper/R7TXB266"},"agent_actions":{"view_html":"https://pith.science/pith/R7TXB266AEIG6BUD2OEV2G3U4P","download_json":"https://pith.science/pith/R7TXB266AEIG6BUD2OEV2G3U4P.json","view_paper":"https://pith.science/paper/R7TXB266","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16002&json=true","fetch_graph":"https://pith.science/api/pith-number/R7TXB266AEIG6BUD2OEV2G3U4P/graph.json","fetch_events":"https://pith.science/api/pith-number/R7TXB266AEIG6BUD2OEV2G3U4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7TXB266AEIG6BUD2OEV2G3U4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7TXB266AEIG6BUD2OEV2G3U4P/action/storage_attestation","attest_author":"https://pith.science/pith/R7TXB266AEIG6BUD2OEV2G3U4P/action/author_attestation","sign_citation":"https://pith.science/pith/R7TXB266AEIG6BUD2OEV2G3U4P/action/citation_signature","submit_replication":"https://pith.science/pith/R7TXB266AEIG6BUD2OEV2G3U4P/action/replication_record"}},"created_at":"2026-07-05T08:01:39.165429+00:00","updated_at":"2026-07-05T08:01:39.165429+00:00"}