{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:RNMQFO7YTZQAZFVNKB6YKSDG7F","short_pith_number":"pith:RNMQFO7Y","schema_version":"1.0","canonical_sha256":"8b5902bbf89e600c96ad507d854866f9739742652bf65a36170284421c7ee32f","source":{"kind":"arxiv","id":"1703.08764","version":1},"attestation_state":"computed","paper":{"title":"Structured Learning of Tree Potentials in CRF for Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Fayao Liu, Guosheng Lin, Ruizhi Qiao","submitted_at":"2017-03-26T04:15:10Z","abstract_excerpt":"We propose a new approach to image segmentation, which exploits the advantages of both conditional random fields (CRFs) and decision trees. In the literature, the potential functions of CRFs are mostly defined as a linear combination of some pre-defined parametric models, and then methods like structured support vector machines (SSVMs) are applied to learn those linear coefficients. We instead formulate the unary and pairwise potentials as nonparametric forests---ensembles of decision trees, and learn the ensemble parameters and the trees in a unified optimization problem within the large-marg"},"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":"1703.08764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-26T04:15:10Z","cross_cats_sorted":[],"title_canon_sha256":"2d394eac0fbc9156a579503f8968b1fbc8a899b6b1d0514a1fa2ce517ec82be3","abstract_canon_sha256":"2ca24f90281e2ba8e5caf5aba7ccc340bc8c13bf80ce61553894b30a865c60ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:55.629688Z","signature_b64":"ONiLuCOtArgM08jTfpJAfGyXbb7u0WiIH/vwtECQILzaZyMPMxly948s8li+ERU2Felv/4Ba6rP0tzYzwct9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b5902bbf89e600c96ad507d854866f9739742652bf65a36170284421c7ee32f","last_reissued_at":"2026-05-18T00:47:55.629060Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:55.629060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Learning of Tree Potentials in CRF for Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Fayao Liu, Guosheng Lin, Ruizhi Qiao","submitted_at":"2017-03-26T04:15:10Z","abstract_excerpt":"We propose a new approach to image segmentation, which exploits the advantages of both conditional random fields (CRFs) and decision trees. In the literature, the potential functions of CRFs are mostly defined as a linear combination of some pre-defined parametric models, and then methods like structured support vector machines (SSVMs) are applied to learn those linear coefficients. We instead formulate the unary and pairwise potentials as nonparametric forests---ensembles of decision trees, and learn the ensemble parameters and the trees in a unified optimization problem within the large-marg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08764","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":""},"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":"1703.08764","created_at":"2026-05-18T00:47:55.629153+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.08764v1","created_at":"2026-05-18T00:47:55.629153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08764","created_at":"2026-05-18T00:47:55.629153+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNMQFO7YTZQA","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNMQFO7YTZQAZFVN","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNMQFO7Y","created_at":"2026-05-18T12:31:39.905425+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/RNMQFO7YTZQAZFVNKB6YKSDG7F","json":"https://pith.science/pith/RNMQFO7YTZQAZFVNKB6YKSDG7F.json","graph_json":"https://pith.science/api/pith-number/RNMQFO7YTZQAZFVNKB6YKSDG7F/graph.json","events_json":"https://pith.science/api/pith-number/RNMQFO7YTZQAZFVNKB6YKSDG7F/events.json","paper":"https://pith.science/paper/RNMQFO7Y"},"agent_actions":{"view_html":"https://pith.science/pith/RNMQFO7YTZQAZFVNKB6YKSDG7F","download_json":"https://pith.science/pith/RNMQFO7YTZQAZFVNKB6YKSDG7F.json","view_paper":"https://pith.science/paper/RNMQFO7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.08764&json=true","fetch_graph":"https://pith.science/api/pith-number/RNMQFO7YTZQAZFVNKB6YKSDG7F/graph.json","fetch_events":"https://pith.science/api/pith-number/RNMQFO7YTZQAZFVNKB6YKSDG7F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNMQFO7YTZQAZFVNKB6YKSDG7F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNMQFO7YTZQAZFVNKB6YKSDG7F/action/storage_attestation","attest_author":"https://pith.science/pith/RNMQFO7YTZQAZFVNKB6YKSDG7F/action/author_attestation","sign_citation":"https://pith.science/pith/RNMQFO7YTZQAZFVNKB6YKSDG7F/action/citation_signature","submit_replication":"https://pith.science/pith/RNMQFO7YTZQAZFVNKB6YKSDG7F/action/replication_record"}},"created_at":"2026-05-18T00:47:55.629153+00:00","updated_at":"2026-05-18T00:47:55.629153+00:00"}