{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YIZ5K3WCH4BEDLKMARGLN4DAXU","short_pith_number":"pith:YIZ5K3WC","schema_version":"1.0","canonical_sha256":"c233d56ec23f0241ad4c044cb6f060bd1b741c71675900ef61ee8b0a840a72ba","source":{"kind":"arxiv","id":"2406.06908","version":1},"attestation_state":"computed","paper":{"title":"UVIS: Unsupervised Video Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Kamal Gupta, Sai Saketh Rambhatla, Saksham Suri, Ser-Nam Lim, Shuaiyi Huang","submitted_at":"2024-06-11T03:05:50Z","abstract_excerpt":"Video instance segmentation requires classifying, segmenting, and tracking every object across video frames. Unlike existing approaches that rely on masks, boxes, or category labels, we propose UVIS, a novel Unsupervised Video Instance Segmentation (UVIS) framework that can perform video instance segmentation without any video annotations or dense label-based pretraining. Our key insight comes from leveraging the dense shape prior from the self-supervised vision foundation model DINO and the openset recognition ability from the image-caption supervised vision-language model CLIP. Our UVIS fram"},"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":"2406.06908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T03:05:50Z","cross_cats_sorted":[],"title_canon_sha256":"cd11328836e2f4db25dfe2d794aba9bb01e4b0b07b9ec73753d009468f54e1e7","abstract_canon_sha256":"0b9884a355d8f36bb8d094c0c0a3eba488ccae33120e6b512698447f45186eb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:15.293362Z","signature_b64":"m4HEj4iWNpv+/9mJp3lI8W0Bg79FKSB/dlORSicPdP9GVLAifHAzIDKa11zVvlDlLtx4z+KhBSSo1nySNYSpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c233d56ec23f0241ad4c044cb6f060bd1b741c71675900ef61ee8b0a840a72ba","last_reissued_at":"2026-07-05T08:30:15.292876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:15.292876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UVIS: Unsupervised Video Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Kamal Gupta, Sai Saketh Rambhatla, Saksham Suri, Ser-Nam Lim, Shuaiyi Huang","submitted_at":"2024-06-11T03:05:50Z","abstract_excerpt":"Video instance segmentation requires classifying, segmenting, and tracking every object across video frames. Unlike existing approaches that rely on masks, boxes, or category labels, we propose UVIS, a novel Unsupervised Video Instance Segmentation (UVIS) framework that can perform video instance segmentation without any video annotations or dense label-based pretraining. Our key insight comes from leveraging the dense shape prior from the self-supervised vision foundation model DINO and the openset recognition ability from the image-caption supervised vision-language model CLIP. Our UVIS fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06908","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/2406.06908/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":"2406.06908","created_at":"2026-07-05T08:30:15.292955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06908v1","created_at":"2026-07-05T08:30:15.292955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06908","created_at":"2026-07-05T08:30:15.292955+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIZ5K3WCH4BE","created_at":"2026-07-05T08:30:15.292955+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIZ5K3WCH4BEDLKM","created_at":"2026-07-05T08:30:15.292955+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIZ5K3WC","created_at":"2026-07-05T08:30:15.292955+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/YIZ5K3WCH4BEDLKMARGLN4DAXU","json":"https://pith.science/pith/YIZ5K3WCH4BEDLKMARGLN4DAXU.json","graph_json":"https://pith.science/api/pith-number/YIZ5K3WCH4BEDLKMARGLN4DAXU/graph.json","events_json":"https://pith.science/api/pith-number/YIZ5K3WCH4BEDLKMARGLN4DAXU/events.json","paper":"https://pith.science/paper/YIZ5K3WC"},"agent_actions":{"view_html":"https://pith.science/pith/YIZ5K3WCH4BEDLKMARGLN4DAXU","download_json":"https://pith.science/pith/YIZ5K3WCH4BEDLKMARGLN4DAXU.json","view_paper":"https://pith.science/paper/YIZ5K3WC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06908&json=true","fetch_graph":"https://pith.science/api/pith-number/YIZ5K3WCH4BEDLKMARGLN4DAXU/graph.json","fetch_events":"https://pith.science/api/pith-number/YIZ5K3WCH4BEDLKMARGLN4DAXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIZ5K3WCH4BEDLKMARGLN4DAXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIZ5K3WCH4BEDLKMARGLN4DAXU/action/storage_attestation","attest_author":"https://pith.science/pith/YIZ5K3WCH4BEDLKMARGLN4DAXU/action/author_attestation","sign_citation":"https://pith.science/pith/YIZ5K3WCH4BEDLKMARGLN4DAXU/action/citation_signature","submit_replication":"https://pith.science/pith/YIZ5K3WCH4BEDLKMARGLN4DAXU/action/replication_record"}},"created_at":"2026-07-05T08:30:15.292955+00:00","updated_at":"2026-07-05T08:30:15.292955+00:00"}