{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VGTFXMA2X7UVQMVERMJQPJV6IG","short_pith_number":"pith:VGTFXMA2","schema_version":"1.0","canonical_sha256":"a9a65bb01abfe95832a48b1307a6be418a63edeeb0399cccfbb3e92c0d8f4f9a","source":{"kind":"arxiv","id":"2307.01197","version":2},"attestation_state":"computed","paper":{"title":"Segment Anything Meets Point Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang, Fisher Yu, Frano Raji\\v{c}, Lei Ke, Martin Danelljan, Yu-Wing Tai","submitted_at":"2023-07-03T17:58:01Z","abstract_excerpt":"The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, enabled by efficient point-centric annotation and prompt-based models. While click and brush interactions are both well explored in interactive image segmentation, the existing methods on videos focus on mask annotation and propagation. This paper presents SAM-PT, a novel method for point-centric interactive video segmentation, empowered by SAM and long-term point tracking. SAM-PT leverages robust and sparse point selection and propagation techniques for mask generation. Compared to tradit"},"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":"2307.01197","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-03T17:58:01Z","cross_cats_sorted":[],"title_canon_sha256":"b9890665f3a695963691beced47f43a2fea48e3c627fae6c1bfd84cface78399","abstract_canon_sha256":"b7f90926347ac3f3f477cb5f342f68b6c075cfb0ad21c2536a9555b6a76e7e10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:46.956518Z","signature_b64":"z8SvMNKpSWLrccTojFmjj/rk+y3zPxYwJaNtqhdmkDMb0Aqp79Zp5/icIn3mWu5VAx82H0DCQHmCPivkJ+GtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9a65bb01abfe95832a48b1307a6be418a63edeeb0399cccfbb3e92c0d8f4f9a","last_reissued_at":"2026-07-05T07:19:46.956039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:46.956039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segment Anything Meets Point Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang, Fisher Yu, Frano Raji\\v{c}, Lei Ke, Martin Danelljan, Yu-Wing Tai","submitted_at":"2023-07-03T17:58:01Z","abstract_excerpt":"The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, enabled by efficient point-centric annotation and prompt-based models. While click and brush interactions are both well explored in interactive image segmentation, the existing methods on videos focus on mask annotation and propagation. This paper presents SAM-PT, a novel method for point-centric interactive video segmentation, empowered by SAM and long-term point tracking. SAM-PT leverages robust and sparse point selection and propagation techniques for mask generation. Compared to tradit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01197","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/2307.01197/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":"2307.01197","created_at":"2026-07-05T07:19:46.956091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01197v2","created_at":"2026-07-05T07:19:46.956091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01197","created_at":"2026-07-05T07:19:46.956091+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGTFXMA2X7UV","created_at":"2026-07-05T07:19:46.956091+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGTFXMA2X7UVQMVE","created_at":"2026-07-05T07:19:46.956091+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGTFXMA2","created_at":"2026-07-05T07:19:46.956091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.11441","citing_title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2408.00714","citing_title":"SAM 2: Segment Anything in Images and Videos","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGTFXMA2X7UVQMVERMJQPJV6IG","json":"https://pith.science/pith/VGTFXMA2X7UVQMVERMJQPJV6IG.json","graph_json":"https://pith.science/api/pith-number/VGTFXMA2X7UVQMVERMJQPJV6IG/graph.json","events_json":"https://pith.science/api/pith-number/VGTFXMA2X7UVQMVERMJQPJV6IG/events.json","paper":"https://pith.science/paper/VGTFXMA2"},"agent_actions":{"view_html":"https://pith.science/pith/VGTFXMA2X7UVQMVERMJQPJV6IG","download_json":"https://pith.science/pith/VGTFXMA2X7UVQMVERMJQPJV6IG.json","view_paper":"https://pith.science/paper/VGTFXMA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01197&json=true","fetch_graph":"https://pith.science/api/pith-number/VGTFXMA2X7UVQMVERMJQPJV6IG/graph.json","fetch_events":"https://pith.science/api/pith-number/VGTFXMA2X7UVQMVERMJQPJV6IG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGTFXMA2X7UVQMVERMJQPJV6IG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGTFXMA2X7UVQMVERMJQPJV6IG/action/storage_attestation","attest_author":"https://pith.science/pith/VGTFXMA2X7UVQMVERMJQPJV6IG/action/author_attestation","sign_citation":"https://pith.science/pith/VGTFXMA2X7UVQMVERMJQPJV6IG/action/citation_signature","submit_replication":"https://pith.science/pith/VGTFXMA2X7UVQMVERMJQPJV6IG/action/replication_record"}},"created_at":"2026-07-05T07:19:46.956091+00:00","updated_at":"2026-07-05T07:19:46.956091+00:00"}