{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ARWCQHCMQKQE55GTS2RQSIIFJX","short_pith_number":"pith:ARWCQHCM","schema_version":"1.0","canonical_sha256":"046c281c4c82a04ef4d396a30921054dc2d9d45603175ad08882743eb3de7b52","source":{"kind":"arxiv","id":"1803.03474","version":3},"attestation_state":"computed","paper":{"title":"An end-to-end TextSpotter with Explicit Alignment and Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changming Sun, Chunhua Shen, Tong He, Weilin Huang, Yu Qiao, Zhi Tian","submitted_at":"2018-03-09T11:30:51Z","abstract_excerpt":"Text detection and recognition in natural images have long been considered as two separate tasks that are processed sequentially. Training of two tasks in a unified framework is non-trivial due to significant dif- ferences in optimisation difficulties. In this work, we present a conceptually simple yet efficient framework that simultaneously processes the two tasks in one shot. Our main contributions are three-fold: 1) we propose a novel text-alignment layer that allows it to precisely compute convolutional features of a text instance in ar- bitrary orientation, which is the key to boost the p"},"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":"1803.03474","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-09T11:30:51Z","cross_cats_sorted":[],"title_canon_sha256":"ee03ca1f7567d0e47f7b2f724218bce640ff2c9af022e72638d87f636c9c5ca1","abstract_canon_sha256":"d8016d8c9b5431382dcf9c3a83f43d4889573fc3ad39c521bf59174f5d19d6ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:21.672090Z","signature_b64":"TrocIrDm6AWe7Pu68swvhshFeypHckGoS59oawJjTEnhcOjdIOTuILHACnrMSKyUvL446p6OBGP3L4pf01uxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"046c281c4c82a04ef4d396a30921054dc2d9d45603175ad08882743eb3de7b52","last_reissued_at":"2026-05-18T00:20:21.671458Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:21.671458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An end-to-end TextSpotter with Explicit Alignment and Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changming Sun, Chunhua Shen, Tong He, Weilin Huang, Yu Qiao, Zhi Tian","submitted_at":"2018-03-09T11:30:51Z","abstract_excerpt":"Text detection and recognition in natural images have long been considered as two separate tasks that are processed sequentially. Training of two tasks in a unified framework is non-trivial due to significant dif- ferences in optimisation difficulties. In this work, we present a conceptually simple yet efficient framework that simultaneously processes the two tasks in one shot. Our main contributions are three-fold: 1) we propose a novel text-alignment layer that allows it to precisely compute convolutional features of a text instance in ar- bitrary orientation, which is the key to boost the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.03474","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":"1803.03474","created_at":"2026-05-18T00:20:21.671548+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.03474v3","created_at":"2026-05-18T00:20:21.671548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.03474","created_at":"2026-05-18T00:20:21.671548+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARWCQHCMQKQE","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARWCQHCMQKQE55GT","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARWCQHCM","created_at":"2026-05-18T12:32:13.499390+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":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARWCQHCMQKQE55GTS2RQSIIFJX","json":"https://pith.science/pith/ARWCQHCMQKQE55GTS2RQSIIFJX.json","graph_json":"https://pith.science/api/pith-number/ARWCQHCMQKQE55GTS2RQSIIFJX/graph.json","events_json":"https://pith.science/api/pith-number/ARWCQHCMQKQE55GTS2RQSIIFJX/events.json","paper":"https://pith.science/paper/ARWCQHCM"},"agent_actions":{"view_html":"https://pith.science/pith/ARWCQHCMQKQE55GTS2RQSIIFJX","download_json":"https://pith.science/pith/ARWCQHCMQKQE55GTS2RQSIIFJX.json","view_paper":"https://pith.science/paper/ARWCQHCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.03474&json=true","fetch_graph":"https://pith.science/api/pith-number/ARWCQHCMQKQE55GTS2RQSIIFJX/graph.json","fetch_events":"https://pith.science/api/pith-number/ARWCQHCMQKQE55GTS2RQSIIFJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARWCQHCMQKQE55GTS2RQSIIFJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARWCQHCMQKQE55GTS2RQSIIFJX/action/storage_attestation","attest_author":"https://pith.science/pith/ARWCQHCMQKQE55GTS2RQSIIFJX/action/author_attestation","sign_citation":"https://pith.science/pith/ARWCQHCMQKQE55GTS2RQSIIFJX/action/citation_signature","submit_replication":"https://pith.science/pith/ARWCQHCMQKQE55GTS2RQSIIFJX/action/replication_record"}},"created_at":"2026-05-18T00:20:21.671548+00:00","updated_at":"2026-05-18T00:20:21.671548+00:00"}