{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ITHNZCT3DYWDJMB455FVQZGQ6F","short_pith_number":"pith:ITHNZCT3","schema_version":"1.0","canonical_sha256":"44cedc8a7b1e2c34b03cef4b5864d0f14416c6ba68a28c022ce7e68abe484c77","source":{"kind":"arxiv","id":"1712.07487","version":1},"attestation_state":"computed","paper":{"title":"Attribute CNNs for Word Spotting in Handwritten Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gernot Fink, Sebastian Sudholt","submitted_at":"2017-12-20T14:11:27Z","abstract_excerpt":"Word spotting has become a field of strong research interest in document image analysis over the last years. Recently, AttributeSVMs were proposed which predict a binary attribute representation. At their time, this influential method defined the state-of-the-art in segmentation-based word spotting. In this work, we present an approach for learning attribute representations with Convolutional Neural Networks (CNNs). By taking a probabilistic perspective on training CNNs, we derive two different loss functions for binary and real-valued word string embeddings. In addition, we propose two differ"},"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":"1712.07487","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-20T14:11:27Z","cross_cats_sorted":[],"title_canon_sha256":"30c24dba244487954763d440545147e48a7bd0009269ba134748442a4cd53c6c","abstract_canon_sha256":"412007315e7868dd4fc26f9285908eee2a0f7f1a87d77b95f654eb6bc45bd4db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:34.411972Z","signature_b64":"VHiZsULnDLHH7RI+BUZ5N/dmqtY+mMVc9TJFnYjk9Ks9aR0QQr/xaqMfSCMnKmCeXqn52Jaisf3coy23yAN6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44cedc8a7b1e2c34b03cef4b5864d0f14416c6ba68a28c022ce7e68abe484c77","last_reissued_at":"2026-05-18T00:27:34.411234Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:34.411234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attribute CNNs for Word Spotting in Handwritten Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gernot Fink, Sebastian Sudholt","submitted_at":"2017-12-20T14:11:27Z","abstract_excerpt":"Word spotting has become a field of strong research interest in document image analysis over the last years. Recently, AttributeSVMs were proposed which predict a binary attribute representation. At their time, this influential method defined the state-of-the-art in segmentation-based word spotting. In this work, we present an approach for learning attribute representations with Convolutional Neural Networks (CNNs). By taking a probabilistic perspective on training CNNs, we derive two different loss functions for binary and real-valued word string embeddings. In addition, we propose two differ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07487","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":"1712.07487","created_at":"2026-05-18T00:27:34.411379+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.07487v1","created_at":"2026-05-18T00:27:34.411379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07487","created_at":"2026-05-18T00:27:34.411379+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITHNZCT3DYWD","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITHNZCT3DYWDJMB4","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITHNZCT3","created_at":"2026-05-18T12:31:21.493067+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/ITHNZCT3DYWDJMB455FVQZGQ6F","json":"https://pith.science/pith/ITHNZCT3DYWDJMB455FVQZGQ6F.json","graph_json":"https://pith.science/api/pith-number/ITHNZCT3DYWDJMB455FVQZGQ6F/graph.json","events_json":"https://pith.science/api/pith-number/ITHNZCT3DYWDJMB455FVQZGQ6F/events.json","paper":"https://pith.science/paper/ITHNZCT3"},"agent_actions":{"view_html":"https://pith.science/pith/ITHNZCT3DYWDJMB455FVQZGQ6F","download_json":"https://pith.science/pith/ITHNZCT3DYWDJMB455FVQZGQ6F.json","view_paper":"https://pith.science/paper/ITHNZCT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.07487&json=true","fetch_graph":"https://pith.science/api/pith-number/ITHNZCT3DYWDJMB455FVQZGQ6F/graph.json","fetch_events":"https://pith.science/api/pith-number/ITHNZCT3DYWDJMB455FVQZGQ6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITHNZCT3DYWDJMB455FVQZGQ6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITHNZCT3DYWDJMB455FVQZGQ6F/action/storage_attestation","attest_author":"https://pith.science/pith/ITHNZCT3DYWDJMB455FVQZGQ6F/action/author_attestation","sign_citation":"https://pith.science/pith/ITHNZCT3DYWDJMB455FVQZGQ6F/action/citation_signature","submit_replication":"https://pith.science/pith/ITHNZCT3DYWDJMB455FVQZGQ6F/action/replication_record"}},"created_at":"2026-05-18T00:27:34.411379+00:00","updated_at":"2026-05-18T00:27:34.411379+00:00"}