{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6YTKEHJB4PAG35DOXMGILKCFM6","short_pith_number":"pith:6YTKEHJB","schema_version":"1.0","canonical_sha256":"f626a21d21e3c06df46ebb0c85a84567a64679fb421ea350977e07f840919897","source":{"kind":"arxiv","id":"2403.14548","version":2},"attestation_state":"computed","paper":{"title":"DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Assaf Singer, Narek Tumanyan, Shai Bagon, Tali Dekel","submitted_at":"2024-03-21T16:49:20Z","abstract_excerpt":"We present DINO-Tracker -- a new framework for long-term dense tracking in video. The pillar of our approach is combining test-time training on a single video, with the powerful localized semantic features learned by a pre-trained DINO-ViT model. Specifically, our framework simultaneously adopts DINO's features to fit to the motion observations of the test video, while training a tracker that directly leverages the refined features. The entire framework is trained end-to-end using a combination of self-supervised losses, and regularization that allows us to retain and benefit from DINO's seman"},"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":"2403.14548","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T16:49:20Z","cross_cats_sorted":[],"title_canon_sha256":"0a0b301a74077eb938624b1973a62c9cbd52170c8bdc282a4b852ef51c8ac9ca","abstract_canon_sha256":"43f53f83e9d94351c8a2f6ccc19e303355be17f34b016fad8d72e76e34e394e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:34.609797Z","signature_b64":"UyKLmvs739gYTVbKzKSf5Xry94YTQeHRHYG26QBfXmbaINBLRrYsnokLZio6PFzBc+QOIPveFBuIN9ueTMtADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f626a21d21e3c06df46ebb0c85a84567a64679fb421ea350977e07f840919897","last_reissued_at":"2026-07-05T08:42:34.609313Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:34.609313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Assaf Singer, Narek Tumanyan, Shai Bagon, Tali Dekel","submitted_at":"2024-03-21T16:49:20Z","abstract_excerpt":"We present DINO-Tracker -- a new framework for long-term dense tracking in video. The pillar of our approach is combining test-time training on a single video, with the powerful localized semantic features learned by a pre-trained DINO-ViT model. Specifically, our framework simultaneously adopts DINO's features to fit to the motion observations of the test video, while training a tracker that directly leverages the refined features. The entire framework is trained end-to-end using a combination of self-supervised losses, and regularization that allows us to retain and benefit from DINO's seman"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14548","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/2403.14548/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":"2403.14548","created_at":"2026-07-05T08:42:34.609387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14548v2","created_at":"2026-07-05T08:42:34.609387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14548","created_at":"2026-07-05T08:42:34.609387+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YTKEHJB4PAG","created_at":"2026-07-05T08:42:34.609387+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YTKEHJB4PAG35DO","created_at":"2026-07-05T08:42:34.609387+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YTKEHJB","created_at":"2026-07-05T08:42:34.609387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05543","citing_title":"FRAME: Pre-Training Video Feature Representations via Anticipation and Memory","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6YTKEHJB4PAG35DOXMGILKCFM6","json":"https://pith.science/pith/6YTKEHJB4PAG35DOXMGILKCFM6.json","graph_json":"https://pith.science/api/pith-number/6YTKEHJB4PAG35DOXMGILKCFM6/graph.json","events_json":"https://pith.science/api/pith-number/6YTKEHJB4PAG35DOXMGILKCFM6/events.json","paper":"https://pith.science/paper/6YTKEHJB"},"agent_actions":{"view_html":"https://pith.science/pith/6YTKEHJB4PAG35DOXMGILKCFM6","download_json":"https://pith.science/pith/6YTKEHJB4PAG35DOXMGILKCFM6.json","view_paper":"https://pith.science/paper/6YTKEHJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14548&json=true","fetch_graph":"https://pith.science/api/pith-number/6YTKEHJB4PAG35DOXMGILKCFM6/graph.json","fetch_events":"https://pith.science/api/pith-number/6YTKEHJB4PAG35DOXMGILKCFM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YTKEHJB4PAG35DOXMGILKCFM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YTKEHJB4PAG35DOXMGILKCFM6/action/storage_attestation","attest_author":"https://pith.science/pith/6YTKEHJB4PAG35DOXMGILKCFM6/action/author_attestation","sign_citation":"https://pith.science/pith/6YTKEHJB4PAG35DOXMGILKCFM6/action/citation_signature","submit_replication":"https://pith.science/pith/6YTKEHJB4PAG35DOXMGILKCFM6/action/replication_record"}},"created_at":"2026-07-05T08:42:34.609387+00:00","updated_at":"2026-07-05T08:42:34.609387+00:00"}