{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:4KOSR4GOMN223FG4QK4EX6SQJF","short_pith_number":"pith:4KOSR4GO","schema_version":"1.0","canonical_sha256":"e29d28f0ce6375ad94dc82b84bfa5049726290126346c07caa37a670b04c7ab5","source":{"kind":"arxiv","id":"1502.03240","version":3},"attestation_state":"computed","paper":{"title":"Conditional Random Fields as Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernardino Romera-Paredes, Chang Huang, Dalong Du, Philip H. S. Torr, Sadeep Jayasumana, Shuai Zheng, Vibhav Vineet, Zhizhong Su","submitted_at":"2015-02-11T10:02:50Z","abstract_excerpt":"Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate visual objects. To solve this problem, we introduce a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To"},"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":"1502.03240","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-02-11T10:02:50Z","cross_cats_sorted":[],"title_canon_sha256":"bd191079594a4be8cf6c0fc40c73c7532973ab3981c7a869f4f5929230faaa43","abstract_canon_sha256":"46bfc39cd5139ace776d9f8b42a65a00e7a848de2599f399b781e672a1334970"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:10.210417Z","signature_b64":"8wxjhSJF3ScSScirKhQ2EVkjSwz3MSICkIpsqBUax6CojBIK8xgLyyC9Dw3GBfD1o+QwyRrllBULdzFYPAYCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e29d28f0ce6375ad94dc82b84bfa5049726290126346c07caa37a670b04c7ab5","last_reissued_at":"2026-05-18T01:17:10.209866Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:10.209866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Random Fields as Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernardino Romera-Paredes, Chang Huang, Dalong Du, Philip H. S. Torr, Sadeep Jayasumana, Shuai Zheng, Vibhav Vineet, Zhizhong Su","submitted_at":"2015-02-11T10:02:50Z","abstract_excerpt":"Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate visual objects. To solve this problem, we introduce a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.03240","kind":"arxiv","version":3},"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":"1502.03240","created_at":"2026-05-18T01:17:10.209943+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.03240v3","created_at":"2026-05-18T01:17:10.209943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.03240","created_at":"2026-05-18T01:17:10.209943+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KOSR4GOMN22","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KOSR4GOMN223FG4","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KOSR4GO","created_at":"2026-05-18T12:29:05.191682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04637","citing_title":"Multi-Person tracking by multi-scale detection in Basketball scenarios","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4KOSR4GOMN223FG4QK4EX6SQJF","json":"https://pith.science/pith/4KOSR4GOMN223FG4QK4EX6SQJF.json","graph_json":"https://pith.science/api/pith-number/4KOSR4GOMN223FG4QK4EX6SQJF/graph.json","events_json":"https://pith.science/api/pith-number/4KOSR4GOMN223FG4QK4EX6SQJF/events.json","paper":"https://pith.science/paper/4KOSR4GO"},"agent_actions":{"view_html":"https://pith.science/pith/4KOSR4GOMN223FG4QK4EX6SQJF","download_json":"https://pith.science/pith/4KOSR4GOMN223FG4QK4EX6SQJF.json","view_paper":"https://pith.science/paper/4KOSR4GO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.03240&json=true","fetch_graph":"https://pith.science/api/pith-number/4KOSR4GOMN223FG4QK4EX6SQJF/graph.json","fetch_events":"https://pith.science/api/pith-number/4KOSR4GOMN223FG4QK4EX6SQJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KOSR4GOMN223FG4QK4EX6SQJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KOSR4GOMN223FG4QK4EX6SQJF/action/storage_attestation","attest_author":"https://pith.science/pith/4KOSR4GOMN223FG4QK4EX6SQJF/action/author_attestation","sign_citation":"https://pith.science/pith/4KOSR4GOMN223FG4QK4EX6SQJF/action/citation_signature","submit_replication":"https://pith.science/pith/4KOSR4GOMN223FG4QK4EX6SQJF/action/replication_record"}},"created_at":"2026-05-18T01:17:10.209943+00:00","updated_at":"2026-05-18T01:17:10.209943+00:00"}