{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AOKEJH5F3JV2GUD2N5NRHXT7VB","short_pith_number":"pith:AOKEJH5F","schema_version":"1.0","canonical_sha256":"0394449fa5da6ba3507a6f5b13de7fa84d9c68c6727c698ca2d4151cabb0632f","source":{"kind":"arxiv","id":"1811.11611","version":2},"attestation_state":"computed","paper":{"title":"A Generative Appearance Model for End-to-end Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Emil Brissman, Fahad Shahbaz Khan, Joakim Johnander, Martin Danelljan, Michael Felsberg","submitted_at":"2018-11-28T15:11:43Z","abstract_excerpt":"One of the fundamental challenges in video object segmentation is to find an effective representation of the target and background appearance. The best performing approaches resort to extensive fine-tuning of a convolutional neural network for this purpose. Besides being prohibitively expensive, this strategy cannot be truly trained end-to-end since the online fine-tuning procedure is not integrated into the offline training of the network.\n  To address these issues, we propose a network architecture that learns a powerful representation of the target and background appearance in a single forw"},"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":"1811.11611","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-28T15:11:43Z","cross_cats_sorted":[],"title_canon_sha256":"c2b8632d8c184773093ca955a47d5a15546ac7b887087610df709266ed2ae8d0","abstract_canon_sha256":"00f4ffea16168ccefe42122ccbe9b0860e9aceb8fae50e83ba8edc5cbe1e66c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:52.359182Z","signature_b64":"Mz8YhpUYS1lU/P2TO8qu9+FDlLQCIHRmsOTmbJy+Cr0nHwbyAPySAiu1JBzJwAUEe5MQr46lheLEqBXM5NeEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0394449fa5da6ba3507a6f5b13de7fa84d9c68c6727c698ca2d4151cabb0632f","last_reissued_at":"2026-05-17T23:58:52.358680Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:52.358680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Generative Appearance Model for End-to-end Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Emil Brissman, Fahad Shahbaz Khan, Joakim Johnander, Martin Danelljan, Michael Felsberg","submitted_at":"2018-11-28T15:11:43Z","abstract_excerpt":"One of the fundamental challenges in video object segmentation is to find an effective representation of the target and background appearance. The best performing approaches resort to extensive fine-tuning of a convolutional neural network for this purpose. Besides being prohibitively expensive, this strategy cannot be truly trained end-to-end since the online fine-tuning procedure is not integrated into the offline training of the network.\n  To address these issues, we propose a network architecture that learns a powerful representation of the target and background appearance in a single forw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11611","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":""},"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":"1811.11611","created_at":"2026-05-17T23:58:52.358756+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.11611v2","created_at":"2026-05-17T23:58:52.358756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11611","created_at":"2026-05-17T23:58:52.358756+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOKEJH5F3JV2","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOKEJH5F3JV2GUD2","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOKEJH5F","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.01203","citing_title":"Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOKEJH5F3JV2GUD2N5NRHXT7VB","json":"https://pith.science/pith/AOKEJH5F3JV2GUD2N5NRHXT7VB.json","graph_json":"https://pith.science/api/pith-number/AOKEJH5F3JV2GUD2N5NRHXT7VB/graph.json","events_json":"https://pith.science/api/pith-number/AOKEJH5F3JV2GUD2N5NRHXT7VB/events.json","paper":"https://pith.science/paper/AOKEJH5F"},"agent_actions":{"view_html":"https://pith.science/pith/AOKEJH5F3JV2GUD2N5NRHXT7VB","download_json":"https://pith.science/pith/AOKEJH5F3JV2GUD2N5NRHXT7VB.json","view_paper":"https://pith.science/paper/AOKEJH5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.11611&json=true","fetch_graph":"https://pith.science/api/pith-number/AOKEJH5F3JV2GUD2N5NRHXT7VB/graph.json","fetch_events":"https://pith.science/api/pith-number/AOKEJH5F3JV2GUD2N5NRHXT7VB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOKEJH5F3JV2GUD2N5NRHXT7VB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOKEJH5F3JV2GUD2N5NRHXT7VB/action/storage_attestation","attest_author":"https://pith.science/pith/AOKEJH5F3JV2GUD2N5NRHXT7VB/action/author_attestation","sign_citation":"https://pith.science/pith/AOKEJH5F3JV2GUD2N5NRHXT7VB/action/citation_signature","submit_replication":"https://pith.science/pith/AOKEJH5F3JV2GUD2N5NRHXT7VB/action/replication_record"}},"created_at":"2026-05-17T23:58:52.358756+00:00","updated_at":"2026-05-17T23:58:52.358756+00:00"}