{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:PSPFNKCRAAF42IP2NHYTV7ZN2J","short_pith_number":"pith:PSPFNKCR","schema_version":"1.0","canonical_sha256":"7c9e56a851000bcd21fa69f13aff2dd27edcd981ada98811610d8e314118a0d4","source":{"kind":"arxiv","id":"1506.04395","version":2},"attestation_state":"computed","paper":{"title":"Reading Scene Text in Deep Convolutional Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Pan He, Weilin Huang, Xiaoou Tang, Yu Qiao","submitted_at":"2015-06-14T13:34:10Z","abstract_excerpt":"We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convolutional neural networks to generate an ordered high-level sequence from a whole word image, avoiding the difficult character segmentation problem. Then a deep recurrent model, building on long short-term memory (LSTM), is developed to robustly recognize the generated CNN sequences, departing from most existing approaches recognising each character independently. Our model has a number of appealing properties in comparison to existing scene t"},"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":"1506.04395","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-14T13:34:10Z","cross_cats_sorted":[],"title_canon_sha256":"5f923fee28559376cdf909457fa78e3f24b95bab35396ffb340a6e857f67f433","abstract_canon_sha256":"06cb1928ed70423f2fc990e82c22b555c5d08391fdfa59917906b0ba40b2f4f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:03.607369Z","signature_b64":"FiDcbFM8R6prCiQQTb8VHet4pcmpB1LYVWn6MVjYaXm5pCRR6lwOPVoh171QmTeJ8hcX6BD1xraPiML4D/7wCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c9e56a851000bcd21fa69f13aff2dd27edcd981ada98811610d8e314118a0d4","last_reissued_at":"2026-05-18T01:24:03.606691Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:03.606691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reading Scene Text in Deep Convolutional Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Pan He, Weilin Huang, Xiaoou Tang, Yu Qiao","submitted_at":"2015-06-14T13:34:10Z","abstract_excerpt":"We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convolutional neural networks to generate an ordered high-level sequence from a whole word image, avoiding the difficult character segmentation problem. Then a deep recurrent model, building on long short-term memory (LSTM), is developed to robustly recognize the generated CNN sequences, departing from most existing approaches recognising each character independently. Our model has a number of appealing properties in comparison to existing scene t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04395","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":"1506.04395","created_at":"2026-05-18T01:24:03.606793+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.04395v2","created_at":"2026-05-18T01:24:03.606793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04395","created_at":"2026-05-18T01:24:03.606793+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSPFNKCRAAF4","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSPFNKCRAAF42IP2","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSPFNKCR","created_at":"2026-05-18T12:29:37.295048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09266","citing_title":"A Multitask Network for Localization and Recognition of Text in Images","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PSPFNKCRAAF42IP2NHYTV7ZN2J","json":"https://pith.science/pith/PSPFNKCRAAF42IP2NHYTV7ZN2J.json","graph_json":"https://pith.science/api/pith-number/PSPFNKCRAAF42IP2NHYTV7ZN2J/graph.json","events_json":"https://pith.science/api/pith-number/PSPFNKCRAAF42IP2NHYTV7ZN2J/events.json","paper":"https://pith.science/paper/PSPFNKCR"},"agent_actions":{"view_html":"https://pith.science/pith/PSPFNKCRAAF42IP2NHYTV7ZN2J","download_json":"https://pith.science/pith/PSPFNKCRAAF42IP2NHYTV7ZN2J.json","view_paper":"https://pith.science/paper/PSPFNKCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.04395&json=true","fetch_graph":"https://pith.science/api/pith-number/PSPFNKCRAAF42IP2NHYTV7ZN2J/graph.json","fetch_events":"https://pith.science/api/pith-number/PSPFNKCRAAF42IP2NHYTV7ZN2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSPFNKCRAAF42IP2NHYTV7ZN2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSPFNKCRAAF42IP2NHYTV7ZN2J/action/storage_attestation","attest_author":"https://pith.science/pith/PSPFNKCRAAF42IP2NHYTV7ZN2J/action/author_attestation","sign_citation":"https://pith.science/pith/PSPFNKCRAAF42IP2NHYTV7ZN2J/action/citation_signature","submit_replication":"https://pith.science/pith/PSPFNKCRAAF42IP2NHYTV7ZN2J/action/replication_record"}},"created_at":"2026-05-18T01:24:03.606793+00:00","updated_at":"2026-05-18T01:24:03.606793+00:00"}