{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7YGCP6YVZC73VLFEBRPU2Y6SXY","short_pith_number":"pith:7YGCP6YV","schema_version":"1.0","canonical_sha256":"fe0c27fb15c8bfbaaca40c5f4d63d2be38e2a1f7d717be9d19bc921fe701a2d2","source":{"kind":"arxiv","id":"2303.10826","version":2},"attestation_state":"computed","paper":{"title":"Visual Prompt Multi-Modal Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Wang, Huchuan Lu, Jiawen Zhu, Simiao Lai, Xin Chen","submitted_at":"2023-03-20T01:51:07Z","abstract_excerpt":"Visible-modal object tracking gives rise to a series of downstream multi-modal tracking tributaries. To inherit the powerful representations of the foundation model, a natural modus operandi for multi-modal tracking is full fine-tuning on the RGB-based parameters. Albeit effective, this manner is not optimal due to the scarcity of downstream data and poor transferability, etc. In this paper, inspired by the recent success of the prompt learning in language models, we develop Visual Prompt multi-modal Tracking (ViPT), which learns the modal-relevant prompts to adapt the frozen pre-trained found"},"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":"2303.10826","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T01:51:07Z","cross_cats_sorted":[],"title_canon_sha256":"9de3e3ecc3e412bdd8e4cc2b079dffb79e82825985c074525a5a2ae92666cf07","abstract_canon_sha256":"c554afaae83c44f06e4aeb5cb4973b3973b05875e1cd74e419c78dd9bd7cb497"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:36.853437Z","signature_b64":"3QU8gaCSvNwpLaIfA2+RgAg9w5wOmokcHtNCb5MkTB+BQ+AuSnoF4SU7+XGGVgr6LkdBoYElsd2DsiyW1KDbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe0c27fb15c8bfbaaca40c5f4d63d2be38e2a1f7d717be9d19bc921fe701a2d2","last_reissued_at":"2026-07-05T05:54:36.852876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:36.852876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Prompt Multi-Modal Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Wang, Huchuan Lu, Jiawen Zhu, Simiao Lai, Xin Chen","submitted_at":"2023-03-20T01:51:07Z","abstract_excerpt":"Visible-modal object tracking gives rise to a series of downstream multi-modal tracking tributaries. To inherit the powerful representations of the foundation model, a natural modus operandi for multi-modal tracking is full fine-tuning on the RGB-based parameters. Albeit effective, this manner is not optimal due to the scarcity of downstream data and poor transferability, etc. In this paper, inspired by the recent success of the prompt learning in language models, we develop Visual Prompt multi-modal Tracking (ViPT), which learns the modal-relevant prompts to adapt the frozen pre-trained found"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10826","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/2303.10826/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":"2303.10826","created_at":"2026-07-05T05:54:36.852952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10826v2","created_at":"2026-07-05T05:54:36.852952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10826","created_at":"2026-07-05T05:54:36.852952+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YGCP6YVZC73","created_at":"2026-07-05T05:54:36.852952+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YGCP6YVZC73VLFE","created_at":"2026-07-05T05:54:36.852952+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YGCP6YV","created_at":"2026-07-05T05:54:36.852952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19990","citing_title":"Progressive Scaling Visual Object Tracking","ref_index":101,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YGCP6YVZC73VLFEBRPU2Y6SXY","json":"https://pith.science/pith/7YGCP6YVZC73VLFEBRPU2Y6SXY.json","graph_json":"https://pith.science/api/pith-number/7YGCP6YVZC73VLFEBRPU2Y6SXY/graph.json","events_json":"https://pith.science/api/pith-number/7YGCP6YVZC73VLFEBRPU2Y6SXY/events.json","paper":"https://pith.science/paper/7YGCP6YV"},"agent_actions":{"view_html":"https://pith.science/pith/7YGCP6YVZC73VLFEBRPU2Y6SXY","download_json":"https://pith.science/pith/7YGCP6YVZC73VLFEBRPU2Y6SXY.json","view_paper":"https://pith.science/paper/7YGCP6YV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10826&json=true","fetch_graph":"https://pith.science/api/pith-number/7YGCP6YVZC73VLFEBRPU2Y6SXY/graph.json","fetch_events":"https://pith.science/api/pith-number/7YGCP6YVZC73VLFEBRPU2Y6SXY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YGCP6YVZC73VLFEBRPU2Y6SXY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YGCP6YVZC73VLFEBRPU2Y6SXY/action/storage_attestation","attest_author":"https://pith.science/pith/7YGCP6YVZC73VLFEBRPU2Y6SXY/action/author_attestation","sign_citation":"https://pith.science/pith/7YGCP6YVZC73VLFEBRPU2Y6SXY/action/citation_signature","submit_replication":"https://pith.science/pith/7YGCP6YVZC73VLFEBRPU2Y6SXY/action/replication_record"}},"created_at":"2026-07-05T05:54:36.852952+00:00","updated_at":"2026-07-05T05:54:36.852952+00:00"}