{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3CIDSYNKZUB627OCO6SWCMYJXE","short_pith_number":"pith:3CIDSYNK","schema_version":"1.0","canonical_sha256":"d8903961aacd03ed7dc277a5613309b920e0c8eed5885e64d932e1f3c7ae0b5c","source":{"kind":"arxiv","id":"2003.11540","version":2},"attestation_state":"computed","paper":{"title":"Learning What to Learn for Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Robinson, Felix J\\\"aremo Lawin, Goutam Bhat, Luc Van Gool, Martin Danelljan, Michael Felsberg, Radu Timofte","submitted_at":"2020-03-25T17:58:43Z","abstract_excerpt":"Video object segmentation (VOS) is a highly challenging problem, since the target object is only defined during inference with a given first-frame reference mask. The problem of how to capture and utilize this limited target information remains a fundamental research question. We address this by introducing an end-to-end trainable VOS architecture that integrates a differentiable few-shot learning module. This internal learner is designed to predict a powerful parametric model of the target by minimizing a segmentation error in the first frame. We further go beyond standard few-shot learning t"},"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":"2003.11540","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-25T17:58:43Z","cross_cats_sorted":[],"title_canon_sha256":"00444d95cadc35bd161377c6b22a424cd941555d2b99e2e0fed63bee89d0d487","abstract_canon_sha256":"0db2d5a195408a0d8e47f85616a0e5de0831ddbd0085c24fbc93c786e15c9fe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:35.980559Z","signature_b64":"BuXzuhIG5U0PnxGBMYkjsXaxLIIYaYGbE/wtO+eF7I+YExrcfgdoK2r1ZvkG49+S7j18HN0wcuiZEG5SUZvGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8903961aacd03ed7dc277a5613309b920e0c8eed5885e64d932e1f3c7ae0b5c","last_reissued_at":"2026-07-05T00:59:35.980098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:35.980098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning What to Learn for Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Robinson, Felix J\\\"aremo Lawin, Goutam Bhat, Luc Van Gool, Martin Danelljan, Michael Felsberg, Radu Timofte","submitted_at":"2020-03-25T17:58:43Z","abstract_excerpt":"Video object segmentation (VOS) is a highly challenging problem, since the target object is only defined during inference with a given first-frame reference mask. The problem of how to capture and utilize this limited target information remains a fundamental research question. We address this by introducing an end-to-end trainable VOS architecture that integrates a differentiable few-shot learning module. This internal learner is designed to predict a powerful parametric model of the target by minimizing a segmentation error in the first frame. We further go beyond standard few-shot learning t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11540","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/2003.11540/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":"2003.11540","created_at":"2026-07-05T00:59:35.980157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.11540v2","created_at":"2026-07-05T00:59:35.980157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11540","created_at":"2026-07-05T00:59:35.980157+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CIDSYNKZUB6","created_at":"2026-07-05T00:59:35.980157+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CIDSYNKZUB627OC","created_at":"2026-07-05T00:59:35.980157+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CIDSYNK","created_at":"2026-07-05T00:59:35.980157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.00714","citing_title":"SAM 2: Segment Anything in Images and Videos","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3CIDSYNKZUB627OCO6SWCMYJXE","json":"https://pith.science/pith/3CIDSYNKZUB627OCO6SWCMYJXE.json","graph_json":"https://pith.science/api/pith-number/3CIDSYNKZUB627OCO6SWCMYJXE/graph.json","events_json":"https://pith.science/api/pith-number/3CIDSYNKZUB627OCO6SWCMYJXE/events.json","paper":"https://pith.science/paper/3CIDSYNK"},"agent_actions":{"view_html":"https://pith.science/pith/3CIDSYNKZUB627OCO6SWCMYJXE","download_json":"https://pith.science/pith/3CIDSYNKZUB627OCO6SWCMYJXE.json","view_paper":"https://pith.science/paper/3CIDSYNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.11540&json=true","fetch_graph":"https://pith.science/api/pith-number/3CIDSYNKZUB627OCO6SWCMYJXE/graph.json","fetch_events":"https://pith.science/api/pith-number/3CIDSYNKZUB627OCO6SWCMYJXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CIDSYNKZUB627OCO6SWCMYJXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CIDSYNKZUB627OCO6SWCMYJXE/action/storage_attestation","attest_author":"https://pith.science/pith/3CIDSYNKZUB627OCO6SWCMYJXE/action/author_attestation","sign_citation":"https://pith.science/pith/3CIDSYNKZUB627OCO6SWCMYJXE/action/citation_signature","submit_replication":"https://pith.science/pith/3CIDSYNKZUB627OCO6SWCMYJXE/action/replication_record"}},"created_at":"2026-07-05T00:59:35.980157+00:00","updated_at":"2026-07-05T00:59:35.980157+00:00"}