{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:U7IHKF7VXRB24FZ3IYNFG7KKEY","short_pith_number":"pith:U7IHKF7V","schema_version":"1.0","canonical_sha256":"a7d07517f5bc43ae173b461a537d4a26225b96c32eaa6a82e71e6890e1bd6c88","source":{"kind":"arxiv","id":"1908.05498","version":1},"attestation_state":"computed","paper":{"title":"A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengquan Zhang, Errui Ding, Fei Qi, Guangming Shi, Jingtuo Liu, Junyu Han, Mengyi En, Pengfei Wang, Zuming Huang","submitted_at":"2019-08-15T11:36:52Z","abstract_excerpt":"Detecting scene text of arbitrary shapes has been a challenging task over the past years. In this paper, we propose a novel segmentation-based text detector, namely SAST, which employs a context attended multi-task learning framework based on a Fully Convolutional Network (FCN) to learn various geometric properties for the reconstruction of polygonal representation of text regions. Taking sequential characteristics of text into consideration, a Context Attention Block is introduced to capture long-range dependencies of pixel information to obtain a more reliable segmentation. In post-processin"},"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":"1908.05498","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-08-15T11:36:52Z","cross_cats_sorted":[],"title_canon_sha256":"882016b8b77dcc5fa4c0dc4dd501e6cd73a9587d510aa0e95b0183c096412009","abstract_canon_sha256":"a7fb633057063dd62281479a361eeccaa0a187d8823c0535d261b38e62e60146"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:56:52.897454Z","signature_b64":"dCn6csI5t9eU6JCyaf5/5vMV3vLUZiYzBnz4OHa7Fhybbb/s0NymD5aEj66ey//kUWcoKomraJ3b4RKKvbI1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7d07517f5bc43ae173b461a537d4a26225b96c32eaa6a82e71e6890e1bd6c88","last_reissued_at":"2026-07-04T23:56:52.896979Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:56:52.896979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengquan Zhang, Errui Ding, Fei Qi, Guangming Shi, Jingtuo Liu, Junyu Han, Mengyi En, Pengfei Wang, Zuming Huang","submitted_at":"2019-08-15T11:36:52Z","abstract_excerpt":"Detecting scene text of arbitrary shapes has been a challenging task over the past years. In this paper, we propose a novel segmentation-based text detector, namely SAST, which employs a context attended multi-task learning framework based on a Fully Convolutional Network (FCN) to learn various geometric properties for the reconstruction of polygonal representation of text regions. Taking sequential characteristics of text into consideration, a Context Attention Block is introduced to capture long-range dependencies of pixel information to obtain a more reliable segmentation. In post-processin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05498","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.05498/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":"1908.05498","created_at":"2026-07-04T23:56:52.897041+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05498v1","created_at":"2026-07-04T23:56:52.897041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05498","created_at":"2026-07-04T23:56:52.897041+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7IHKF7VXRB2","created_at":"2026-07-04T23:56:52.897041+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7IHKF7VXRB24FZ3","created_at":"2026-07-04T23:56:52.897041+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7IHKF7V","created_at":"2026-07-04T23:56:52.897041+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/U7IHKF7VXRB24FZ3IYNFG7KKEY","json":"https://pith.science/pith/U7IHKF7VXRB24FZ3IYNFG7KKEY.json","graph_json":"https://pith.science/api/pith-number/U7IHKF7VXRB24FZ3IYNFG7KKEY/graph.json","events_json":"https://pith.science/api/pith-number/U7IHKF7VXRB24FZ3IYNFG7KKEY/events.json","paper":"https://pith.science/paper/U7IHKF7V"},"agent_actions":{"view_html":"https://pith.science/pith/U7IHKF7VXRB24FZ3IYNFG7KKEY","download_json":"https://pith.science/pith/U7IHKF7VXRB24FZ3IYNFG7KKEY.json","view_paper":"https://pith.science/paper/U7IHKF7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05498&json=true","fetch_graph":"https://pith.science/api/pith-number/U7IHKF7VXRB24FZ3IYNFG7KKEY/graph.json","fetch_events":"https://pith.science/api/pith-number/U7IHKF7VXRB24FZ3IYNFG7KKEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7IHKF7VXRB24FZ3IYNFG7KKEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7IHKF7VXRB24FZ3IYNFG7KKEY/action/storage_attestation","attest_author":"https://pith.science/pith/U7IHKF7VXRB24FZ3IYNFG7KKEY/action/author_attestation","sign_citation":"https://pith.science/pith/U7IHKF7VXRB24FZ3IYNFG7KKEY/action/citation_signature","submit_replication":"https://pith.science/pith/U7IHKF7VXRB24FZ3IYNFG7KKEY/action/replication_record"}},"created_at":"2026-07-04T23:56:52.897041+00:00","updated_at":"2026-07-04T23:56:52.897041+00:00"}