{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:GLEQ2TQCCZRTPCUFFJOM4DL33J","short_pith_number":"pith:GLEQ2TQC","schema_version":"1.0","canonical_sha256":"32c90d4e021663378a852a5cce0d7bda67546c5117adf2e6cc57305d08465f7a","source":{"kind":"arxiv","id":"1503.08263","version":1},"attestation_state":"computed","paper":{"title":"CRF Learning with CNN Features 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","submitted_at":"2015-03-28T04:05:09Z","abstract_excerpt":"Conditional Random Rields (CRF) have been widely applied in image segmentations. While most studies rely on hand-crafted features, we here propose to exploit a pre-trained large convolutional neural network (CNN) to generate deep features for CRF learning. The deep CNN is trained on the ImageNet dataset and transferred to image segmentations here for constructing potentials of superpixels. Then the CRF parameters are learnt using a structured support vector machine (SSVM). To fully exploit context information in inference, we construct spatially related co-occurrence pairwise potentials and in"},"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":"1503.08263","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-03-28T04:05:09Z","cross_cats_sorted":[],"title_canon_sha256":"4687445ff41b85e6f52b90117fc46a2ea83304a481b92850efec5fcaa7be489d","abstract_canon_sha256":"13551176e5f55d4a0db5224df44b785f6bf7b1296c5a85444fbac1b8dec4fd4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:20:02.338382Z","signature_b64":"JMa35WMhkuaqQMc7Dje0CnzVU1DrCOf01R0I3tGkbLc5RYVq8eazcWLK4op+YlCN/Qx1Fy5289Fyj/Y5twryBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32c90d4e021663378a852a5cce0d7bda67546c5117adf2e6cc57305d08465f7a","last_reissued_at":"2026-05-18T02:20:02.337748Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:20:02.337748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRF Learning with CNN Features 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","submitted_at":"2015-03-28T04:05:09Z","abstract_excerpt":"Conditional Random Rields (CRF) have been widely applied in image segmentations. While most studies rely on hand-crafted features, we here propose to exploit a pre-trained large convolutional neural network (CNN) to generate deep features for CRF learning. The deep CNN is trained on the ImageNet dataset and transferred to image segmentations here for constructing potentials of superpixels. Then the CRF parameters are learnt using a structured support vector machine (SSVM). To fully exploit context information in inference, we construct spatially related co-occurrence pairwise potentials and in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.08263","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":"1503.08263","created_at":"2026-05-18T02:20:02.337851+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.08263v1","created_at":"2026-05-18T02:20:02.337851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.08263","created_at":"2026-05-18T02:20:02.337851+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLEQ2TQCCZRT","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLEQ2TQCCZRTPCUF","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLEQ2TQC","created_at":"2026-05-18T12:29:22.688609+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/GLEQ2TQCCZRTPCUFFJOM4DL33J","json":"https://pith.science/pith/GLEQ2TQCCZRTPCUFFJOM4DL33J.json","graph_json":"https://pith.science/api/pith-number/GLEQ2TQCCZRTPCUFFJOM4DL33J/graph.json","events_json":"https://pith.science/api/pith-number/GLEQ2TQCCZRTPCUFFJOM4DL33J/events.json","paper":"https://pith.science/paper/GLEQ2TQC"},"agent_actions":{"view_html":"https://pith.science/pith/GLEQ2TQCCZRTPCUFFJOM4DL33J","download_json":"https://pith.science/pith/GLEQ2TQCCZRTPCUFFJOM4DL33J.json","view_paper":"https://pith.science/paper/GLEQ2TQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.08263&json=true","fetch_graph":"https://pith.science/api/pith-number/GLEQ2TQCCZRTPCUFFJOM4DL33J/graph.json","fetch_events":"https://pith.science/api/pith-number/GLEQ2TQCCZRTPCUFFJOM4DL33J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLEQ2TQCCZRTPCUFFJOM4DL33J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLEQ2TQCCZRTPCUFFJOM4DL33J/action/storage_attestation","attest_author":"https://pith.science/pith/GLEQ2TQCCZRTPCUFFJOM4DL33J/action/author_attestation","sign_citation":"https://pith.science/pith/GLEQ2TQCCZRTPCUFFJOM4DL33J/action/citation_signature","submit_replication":"https://pith.science/pith/GLEQ2TQCCZRTPCUFFJOM4DL33J/action/replication_record"}},"created_at":"2026-05-18T02:20:02.337851+00:00","updated_at":"2026-05-18T02:20:02.337851+00:00"}