{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SKHPKE7Y2LEVT5VS6HQBHAYAPD","short_pith_number":"pith:SKHPKE7Y","schema_version":"1.0","canonical_sha256":"928ef513f8d2c959f6b2f1e013830078eb536bf223f272d298b950af8cc07e9d","source":{"kind":"arxiv","id":"2505.18111","version":1},"attestation_state":"computed","paper":{"title":"Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Yen Yang, Chien-Kai Kuo, Chung-I Huang, Hsiang-Wei Huang, Jenq-Neng Hwang, Jui-Wei Chang, Kwang-Ju Kim, Pyong-Kun Kim","submitted_at":"2025-05-23T17:04:56Z","abstract_excerpt":"We present an effective approach for adapting the Segment Anything Model 2 (SAM2) to the Visual Object Tracking (VOT) task. Our method leverages the powerful pre-trained capabilities of SAM2 and incorporates several key techniques to enhance its performance in VOT applications. By combining SAM2 with our proposed optimizations, we achieved a first place AUC score of 89.4 on the 2024 ICPR Multi-modal Object Tracking challenge, demonstrating the effectiveness of our approach. This paper details our methodology, the specific enhancements made to SAM2, and a comprehensive analysis of our results i"},"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":"2505.18111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T17:04:56Z","cross_cats_sorted":[],"title_canon_sha256":"6d8939f65cf8eb76792e59a83be712727d1e48742ef3304c1276d299d2b4afb3","abstract_canon_sha256":"b76de0b86dfc9e1543a02182623476a92b5ea0350e1c2d3b5bea8b292cf73b37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:36.740440Z","signature_b64":"d6afgeuTCxTzkFDIcunJBanO0e5W16xVq5WCI4KinO+TWWicFOFuUcT6FKY1e4N6Eqxv3h7hHFDzTjLI2Gl8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"928ef513f8d2c959f6b2f1e013830078eb536bf223f272d298b950af8cc07e9d","last_reissued_at":"2026-07-05T11:08:36.739944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:36.739944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Yen Yang, Chien-Kai Kuo, Chung-I Huang, Hsiang-Wei Huang, Jenq-Neng Hwang, Jui-Wei Chang, Kwang-Ju Kim, Pyong-Kun Kim","submitted_at":"2025-05-23T17:04:56Z","abstract_excerpt":"We present an effective approach for adapting the Segment Anything Model 2 (SAM2) to the Visual Object Tracking (VOT) task. Our method leverages the powerful pre-trained capabilities of SAM2 and incorporates several key techniques to enhance its performance in VOT applications. By combining SAM2 with our proposed optimizations, we achieved a first place AUC score of 89.4 on the 2024 ICPR Multi-modal Object Tracking challenge, demonstrating the effectiveness of our approach. This paper details our methodology, the specific enhancements made to SAM2, and a comprehensive analysis of our results i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18111","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/2505.18111/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":"2505.18111","created_at":"2026-07-05T11:08:36.740009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18111v1","created_at":"2026-07-05T11:08:36.740009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18111","created_at":"2026-07-05T11:08:36.740009+00:00"},{"alias_kind":"pith_short_12","alias_value":"SKHPKE7Y2LEV","created_at":"2026-07-05T11:08:36.740009+00:00"},{"alias_kind":"pith_short_16","alias_value":"SKHPKE7Y2LEVT5VS","created_at":"2026-07-05T11:08:36.740009+00:00"},{"alias_kind":"pith_short_8","alias_value":"SKHPKE7Y","created_at":"2026-07-05T11:08:36.740009+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SKHPKE7Y2LEVT5VS6HQBHAYAPD","json":"https://pith.science/pith/SKHPKE7Y2LEVT5VS6HQBHAYAPD.json","graph_json":"https://pith.science/api/pith-number/SKHPKE7Y2LEVT5VS6HQBHAYAPD/graph.json","events_json":"https://pith.science/api/pith-number/SKHPKE7Y2LEVT5VS6HQBHAYAPD/events.json","paper":"https://pith.science/paper/SKHPKE7Y"},"agent_actions":{"view_html":"https://pith.science/pith/SKHPKE7Y2LEVT5VS6HQBHAYAPD","download_json":"https://pith.science/pith/SKHPKE7Y2LEVT5VS6HQBHAYAPD.json","view_paper":"https://pith.science/paper/SKHPKE7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18111&json=true","fetch_graph":"https://pith.science/api/pith-number/SKHPKE7Y2LEVT5VS6HQBHAYAPD/graph.json","fetch_events":"https://pith.science/api/pith-number/SKHPKE7Y2LEVT5VS6HQBHAYAPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SKHPKE7Y2LEVT5VS6HQBHAYAPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SKHPKE7Y2LEVT5VS6HQBHAYAPD/action/storage_attestation","attest_author":"https://pith.science/pith/SKHPKE7Y2LEVT5VS6HQBHAYAPD/action/author_attestation","sign_citation":"https://pith.science/pith/SKHPKE7Y2LEVT5VS6HQBHAYAPD/action/citation_signature","submit_replication":"https://pith.science/pith/SKHPKE7Y2LEVT5VS6HQBHAYAPD/action/replication_record"}},"created_at":"2026-07-05T11:08:36.740009+00:00","updated_at":"2026-07-05T11:08:36.740009+00:00"}