{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NLTYFLZBBDXCF3SRLAFMD626GE","short_pith_number":"pith:NLTYFLZB","schema_version":"1.0","canonical_sha256":"6ae782af2108ee22ee51580ac1fb5e311fdbdde46dfa126c622871f72b9a93b5","source":{"kind":"arxiv","id":"1709.02054","version":3},"attestation_state":"computed","paper":{"title":"Focusing Attention: Towards Accurate Text Recognition in Natural Images","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Bai, Gang Zheng, Shiliang Pu, Shuigeng Zhou, Yunlu Xu, Zhanzhan Cheng","submitted_at":"2017-09-07T02:58:01Z","abstract_excerpt":"Scene text recognition has been a hot research topic in computer vision due to its various applications. The state of the art is the attention-based encoder-decoder framework that learns the mapping between input images and output sequences in a purely data-driven way. However, we observe that existing attention-based methods perform poorly on complicated and/or low-quality images. One major reason is that existing methods cannot get accurate alignments between feature areas and targets for such images. We call this phenomenon \"attention drift\". To tackle this problem, in this paper we propose"},"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":"1709.02054","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2017-09-07T02:58:01Z","cross_cats_sorted":[],"title_canon_sha256":"df12556bd1516e1aff6122800bff34cd95f62bd54cd096dfeef3021139df3438","abstract_canon_sha256":"8cb6f67c037b289d07ee4b3a47f7d830d0b8b2d634aca76bad7fa48e841711dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:20.158192Z","signature_b64":"5YKUkLN6l3VHw9mVJfsRGxyxIVs7Q/5yNlzPgUQMALvupZbNLaE4jM5QEFGDhpv4HUsOMH2YWmwh13t3k4H+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ae782af2108ee22ee51580ac1fb5e311fdbdde46dfa126c622871f72b9a93b5","last_reissued_at":"2026-05-18T00:32:20.157492Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:20.157492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Focusing Attention: Towards Accurate Text Recognition in Natural Images","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Bai, Gang Zheng, Shiliang Pu, Shuigeng Zhou, Yunlu Xu, Zhanzhan Cheng","submitted_at":"2017-09-07T02:58:01Z","abstract_excerpt":"Scene text recognition has been a hot research topic in computer vision due to its various applications. The state of the art is the attention-based encoder-decoder framework that learns the mapping between input images and output sequences in a purely data-driven way. However, we observe that existing attention-based methods perform poorly on complicated and/or low-quality images. One major reason is that existing methods cannot get accurate alignments between feature areas and targets for such images. We call this phenomenon \"attention drift\". To tackle this problem, in this paper we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02054","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":"1709.02054","created_at":"2026-05-18T00:32:20.157602+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.02054v3","created_at":"2026-05-18T00:32:20.157602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02054","created_at":"2026-05-18T00:32:20.157602+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLTYFLZBBDXC","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLTYFLZBBDXCF3SR","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLTYFLZB","created_at":"2026-05-18T12:31:31.346846+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/NLTYFLZBBDXCF3SRLAFMD626GE","json":"https://pith.science/pith/NLTYFLZBBDXCF3SRLAFMD626GE.json","graph_json":"https://pith.science/api/pith-number/NLTYFLZBBDXCF3SRLAFMD626GE/graph.json","events_json":"https://pith.science/api/pith-number/NLTYFLZBBDXCF3SRLAFMD626GE/events.json","paper":"https://pith.science/paper/NLTYFLZB"},"agent_actions":{"view_html":"https://pith.science/pith/NLTYFLZBBDXCF3SRLAFMD626GE","download_json":"https://pith.science/pith/NLTYFLZBBDXCF3SRLAFMD626GE.json","view_paper":"https://pith.science/paper/NLTYFLZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.02054&json=true","fetch_graph":"https://pith.science/api/pith-number/NLTYFLZBBDXCF3SRLAFMD626GE/graph.json","fetch_events":"https://pith.science/api/pith-number/NLTYFLZBBDXCF3SRLAFMD626GE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLTYFLZBBDXCF3SRLAFMD626GE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLTYFLZBBDXCF3SRLAFMD626GE/action/storage_attestation","attest_author":"https://pith.science/pith/NLTYFLZBBDXCF3SRLAFMD626GE/action/author_attestation","sign_citation":"https://pith.science/pith/NLTYFLZBBDXCF3SRLAFMD626GE/action/citation_signature","submit_replication":"https://pith.science/pith/NLTYFLZBBDXCF3SRLAFMD626GE/action/replication_record"}},"created_at":"2026-05-18T00:32:20.157602+00:00","updated_at":"2026-05-18T00:32:20.157602+00:00"}