{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CVVIDQIPBFU5BQF3MFQV2XOL7Y","short_pith_number":"pith:CVVIDQIP","schema_version":"1.0","canonical_sha256":"156a81c10f0969d0c0bb61615d5dcbfe38c1063999e10f0516157f76b1729e6a","source":{"kind":"arxiv","id":"2202.07025","version":2},"attestation_state":"computed","paper":{"title":"Box Supervised Video Segmentation Proposal Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathan Kobold, Matthias Schubert, Rajat Koner, Tanveer Hannan","submitted_at":"2022-02-14T20:38:28Z","abstract_excerpt":"Video Object Segmentation (VOS) has been targeted by various fully-supervised and self-supervised approaches. While fully-supervised methods demonstrate excellent results, self-supervised ones, which do not use pixel-level ground truth, attract much attention. However, self-supervised approaches pose a significant performance gap. Box-level annotations provide a balanced compromise between labeling effort and result quality for image segmentation but have not been exploited for the video domain. In this work, we propose a box-supervised video object segmentation proposal network, which takes a"},"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":"2202.07025","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-14T20:38:28Z","cross_cats_sorted":[],"title_canon_sha256":"96486a5b9a631d1a7ffa6b92d0a068704c1be825c69a21c991df08906ea4ed9e","abstract_canon_sha256":"afdbf55a637081feab3bc38f6fd91fa447acc2456227e83424e95cb873841a59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:43.917419Z","signature_b64":"rJSq0WTyiLoI0gWekTgqLwbJFLkhMl8bCDrdrYczFWRkffAkG4JphH+iHhmgp8QwJOU16NVespeGe+Gj2QSjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"156a81c10f0969d0c0bb61615d5dcbfe38c1063999e10f0516157f76b1729e6a","last_reissued_at":"2026-07-05T03:57:43.916894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:43.916894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Box Supervised Video Segmentation Proposal Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathan Kobold, Matthias Schubert, Rajat Koner, Tanveer Hannan","submitted_at":"2022-02-14T20:38:28Z","abstract_excerpt":"Video Object Segmentation (VOS) has been targeted by various fully-supervised and self-supervised approaches. While fully-supervised methods demonstrate excellent results, self-supervised ones, which do not use pixel-level ground truth, attract much attention. However, self-supervised approaches pose a significant performance gap. Box-level annotations provide a balanced compromise between labeling effort and result quality for image segmentation but have not been exploited for the video domain. In this work, we propose a box-supervised video object segmentation proposal network, which takes a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07025","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/2202.07025/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":"2202.07025","created_at":"2026-07-05T03:57:43.916957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07025v2","created_at":"2026-07-05T03:57:43.916957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07025","created_at":"2026-07-05T03:57:43.916957+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVVIDQIPBFU5","created_at":"2026-07-05T03:57:43.916957+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVVIDQIPBFU5BQF3","created_at":"2026-07-05T03:57:43.916957+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVVIDQIP","created_at":"2026-07-05T03:57:43.916957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17797","citing_title":"Weakly-Supervised Referring Video Object Segmentation through Text Supervision","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CVVIDQIPBFU5BQF3MFQV2XOL7Y","json":"https://pith.science/pith/CVVIDQIPBFU5BQF3MFQV2XOL7Y.json","graph_json":"https://pith.science/api/pith-number/CVVIDQIPBFU5BQF3MFQV2XOL7Y/graph.json","events_json":"https://pith.science/api/pith-number/CVVIDQIPBFU5BQF3MFQV2XOL7Y/events.json","paper":"https://pith.science/paper/CVVIDQIP"},"agent_actions":{"view_html":"https://pith.science/pith/CVVIDQIPBFU5BQF3MFQV2XOL7Y","download_json":"https://pith.science/pith/CVVIDQIPBFU5BQF3MFQV2XOL7Y.json","view_paper":"https://pith.science/paper/CVVIDQIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07025&json=true","fetch_graph":"https://pith.science/api/pith-number/CVVIDQIPBFU5BQF3MFQV2XOL7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/CVVIDQIPBFU5BQF3MFQV2XOL7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVVIDQIPBFU5BQF3MFQV2XOL7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVVIDQIPBFU5BQF3MFQV2XOL7Y/action/storage_attestation","attest_author":"https://pith.science/pith/CVVIDQIPBFU5BQF3MFQV2XOL7Y/action/author_attestation","sign_citation":"https://pith.science/pith/CVVIDQIPBFU5BQF3MFQV2XOL7Y/action/citation_signature","submit_replication":"https://pith.science/pith/CVVIDQIPBFU5BQF3MFQV2XOL7Y/action/replication_record"}},"created_at":"2026-07-05T03:57:43.916957+00:00","updated_at":"2026-07-05T03:57:43.916957+00:00"}