{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U3OUNUOYZ7V5OCUN6LZS3FADNQ","short_pith_number":"pith:U3OUNUOY","schema_version":"1.0","canonical_sha256":"a6dd46d1d8cfebd70a8df2f32d94036c24547493102bad0d26dbadd25539abe6","source":{"kind":"arxiv","id":"2111.02394","version":2},"attestation_state":"computed","paper":{"title":"FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enze Xie, Guo Chen, Jiahao Wang, Ping Luo, Tong Lu, Wenhai Wang, Zhe Chen","submitted_at":"2021-11-03T17:58:47Z","abstract_excerpt":"We propose an accurate and efficient scene text detection framework, termed FAST (i.e., faster arbitrarily-shaped text detector). Different from recent advanced text detectors that used complicated post-processing and hand-crafted network architectures, resulting in low inference speed, FAST has two new designs. (1) We design a minimalist kernel representation (only has 1-channel output) to model text with arbitrary shape, as well as a GPU-parallel post-processing to efficiently assemble text lines with a negligible time overhead. (2) We search the network architecture tailored for text detect"},"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":"2111.02394","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-03T17:58:47Z","cross_cats_sorted":[],"title_canon_sha256":"33ab35d363f32dc5e714e76467171e406aca66508f4289c7ebb174945596bcc0","abstract_canon_sha256":"0d78463e5928265795f906773aba971dcb5ec613c54d04bcc6df73ef54d4dba8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:20.653914Z","signature_b64":"bY+2MlFY9Ioz1SpyksoxG+oTkjW8w3sf1aalSHWMDQCELvRvsRrAJtgZWSeTnDw2uf8LVMleHup32NjikUKeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6dd46d1d8cfebd70a8df2f32d94036c24547493102bad0d26dbadd25539abe6","last_reissued_at":"2026-07-05T05:32:20.653286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:20.653286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enze Xie, Guo Chen, Jiahao Wang, Ping Luo, Tong Lu, Wenhai Wang, Zhe Chen","submitted_at":"2021-11-03T17:58:47Z","abstract_excerpt":"We propose an accurate and efficient scene text detection framework, termed FAST (i.e., faster arbitrarily-shaped text detector). Different from recent advanced text detectors that used complicated post-processing and hand-crafted network architectures, resulting in low inference speed, FAST has two new designs. (1) We design a minimalist kernel representation (only has 1-channel output) to model text with arbitrary shape, as well as a GPU-parallel post-processing to efficiently assemble text lines with a negligible time overhead. (2) We search the network architecture tailored for text detect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02394","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.02394/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2111.02394","created_at":"2026-07-05T05:32:20.653357+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.02394v2","created_at":"2026-07-05T05:32:20.653357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02394","created_at":"2026-07-05T05:32:20.653357+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3OUNUOYZ7V5","created_at":"2026-07-05T05:32:20.653357+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3OUNUOYZ7V5OCUN","created_at":"2026-07-05T05:32:20.653357+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3OUNUOY","created_at":"2026-07-05T05:32:20.653357+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29476","citing_title":"Comparative Evaluation of Machine Translation Systems on Images with Text","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10077","citing_title":"DocRevive: A Unified Pipeline for Document Text Restoration","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10077","citing_title":"DocRevive: A Unified Pipeline for Document Text Restoration","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3OUNUOYZ7V5OCUN6LZS3FADNQ","json":"https://pith.science/pith/U3OUNUOYZ7V5OCUN6LZS3FADNQ.json","graph_json":"https://pith.science/api/pith-number/U3OUNUOYZ7V5OCUN6LZS3FADNQ/graph.json","events_json":"https://pith.science/api/pith-number/U3OUNUOYZ7V5OCUN6LZS3FADNQ/events.json","paper":"https://pith.science/paper/U3OUNUOY"},"agent_actions":{"view_html":"https://pith.science/pith/U3OUNUOYZ7V5OCUN6LZS3FADNQ","download_json":"https://pith.science/pith/U3OUNUOYZ7V5OCUN6LZS3FADNQ.json","view_paper":"https://pith.science/paper/U3OUNUOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.02394&json=true","fetch_graph":"https://pith.science/api/pith-number/U3OUNUOYZ7V5OCUN6LZS3FADNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/U3OUNUOYZ7V5OCUN6LZS3FADNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3OUNUOYZ7V5OCUN6LZS3FADNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3OUNUOYZ7V5OCUN6LZS3FADNQ/action/storage_attestation","attest_author":"https://pith.science/pith/U3OUNUOYZ7V5OCUN6LZS3FADNQ/action/author_attestation","sign_citation":"https://pith.science/pith/U3OUNUOYZ7V5OCUN6LZS3FADNQ/action/citation_signature","submit_replication":"https://pith.science/pith/U3OUNUOYZ7V5OCUN6LZS3FADNQ/action/replication_record"}},"created_at":"2026-07-05T05:32:20.653357+00:00","updated_at":"2026-07-05T05:32:20.653357+00:00"}