{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XNNBRONMITPWMG3ELJDXYAOQMV","short_pith_number":"pith:XNNBRONM","schema_version":"1.0","canonical_sha256":"bb5a18b9ac44df661b645a477c01d06571c2b6ba8759745fb462709612b42307","source":{"kind":"arxiv","id":"2501.12218","version":2},"attestation_state":"computed","paper":{"title":"Exploring Temporally-Aware Features for Point Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"In\\`es Hyeonsu Kim, Jiahui Huang, Joon-Young Lee, Jung Yi, Seokju Cho, Seungryong Kim","submitted_at":"2025-01-21T15:39:40Z","abstract_excerpt":"Point tracking in videos is a fundamental task with applications in robotics, video editing, and more. While many vision tasks benefit from pre-trained feature backbones to improve generalizability, point tracking has primarily relied on simpler backbones trained from scratch on synthetic data, which may limit robustness in real-world scenarios. Additionally, point tracking requires temporal awareness to ensure coherence across frames, but using temporally-aware features is still underexplored. Most current methods often employ a two-stage process: an initial coarse prediction followed by a re"},"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":"2501.12218","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T15:39:40Z","cross_cats_sorted":[],"title_canon_sha256":"aeffbcfd23582e34f8b8cf290c4f748f95af3ef2a5975099c7c9b8c917259d4d","abstract_canon_sha256":"815bab9a556bd58e8912f34aab1111ac972340f7a338c7698a9cabdcbb1aeb15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:31.525530Z","signature_b64":"OQtiXQTXCbtA4U1AUw9CSOa/LkanT0yHFSYOQVK2CeKcuKvrMqVwavHeobEujUjDl0m6H24vc1FENo57t1PeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb5a18b9ac44df661b645a477c01d06571c2b6ba8759745fb462709612b42307","last_reissued_at":"2026-07-05T10:51:31.525031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:31.525031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Temporally-Aware Features for Point Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"In\\`es Hyeonsu Kim, Jiahui Huang, Joon-Young Lee, Jung Yi, Seokju Cho, Seungryong Kim","submitted_at":"2025-01-21T15:39:40Z","abstract_excerpt":"Point tracking in videos is a fundamental task with applications in robotics, video editing, and more. While many vision tasks benefit from pre-trained feature backbones to improve generalizability, point tracking has primarily relied on simpler backbones trained from scratch on synthetic data, which may limit robustness in real-world scenarios. Additionally, point tracking requires temporal awareness to ensure coherence across frames, but using temporally-aware features is still underexplored. Most current methods often employ a two-stage process: an initial coarse prediction followed by a re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12218","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/2501.12218/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":"2501.12218","created_at":"2026-07-05T10:51:31.525097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12218v2","created_at":"2026-07-05T10:51:31.525097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12218","created_at":"2026-07-05T10:51:31.525097+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNNBRONMITPW","created_at":"2026-07-05T10:51:31.525097+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNNBRONMITPWMG3E","created_at":"2026-07-05T10:51:31.525097+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNNBRONM","created_at":"2026-07-05T10:51:31.525097+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/XNNBRONMITPWMG3ELJDXYAOQMV","json":"https://pith.science/pith/XNNBRONMITPWMG3ELJDXYAOQMV.json","graph_json":"https://pith.science/api/pith-number/XNNBRONMITPWMG3ELJDXYAOQMV/graph.json","events_json":"https://pith.science/api/pith-number/XNNBRONMITPWMG3ELJDXYAOQMV/events.json","paper":"https://pith.science/paper/XNNBRONM"},"agent_actions":{"view_html":"https://pith.science/pith/XNNBRONMITPWMG3ELJDXYAOQMV","download_json":"https://pith.science/pith/XNNBRONMITPWMG3ELJDXYAOQMV.json","view_paper":"https://pith.science/paper/XNNBRONM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12218&json=true","fetch_graph":"https://pith.science/api/pith-number/XNNBRONMITPWMG3ELJDXYAOQMV/graph.json","fetch_events":"https://pith.science/api/pith-number/XNNBRONMITPWMG3ELJDXYAOQMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNNBRONMITPWMG3ELJDXYAOQMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNNBRONMITPWMG3ELJDXYAOQMV/action/storage_attestation","attest_author":"https://pith.science/pith/XNNBRONMITPWMG3ELJDXYAOQMV/action/author_attestation","sign_citation":"https://pith.science/pith/XNNBRONMITPWMG3ELJDXYAOQMV/action/citation_signature","submit_replication":"https://pith.science/pith/XNNBRONMITPWMG3ELJDXYAOQMV/action/replication_record"}},"created_at":"2026-07-05T10:51:31.525097+00:00","updated_at":"2026-07-05T10:51:31.525097+00:00"}