{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FGQH3BOGXZDPRWJWPDTRRKP6X4","short_pith_number":"pith:FGQH3BOG","schema_version":"1.0","canonical_sha256":"29a07d85c6be46f8d93678e718a9febf29435f1f2100265b6c306eee805fafbb","source":{"kind":"arxiv","id":"2104.05458","version":1},"attestation_state":"computed","paper":{"title":"PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengquan Zhang, Errui Ding, Fei Qi, Guangming Shi, Jingtuo Liu, Junyu Han, Pengfei Wang, Pengyuan Lyu, Shanshan Liu, Xiaoqiang Zhang","submitted_at":"2021-04-12T13:27:34Z","abstract_excerpt":"The reading of arbitrarily-shaped text has received increasing research attention. However, existing text spotters are mostly built on two-stage frameworks or character-based methods, which suffer from either Non-Maximum Suppression (NMS), Region-of-Interest (RoI) operations, or character-level annotations. In this paper, to address the above problems, we propose a novel fully convolutional Point Gathering Network (PGNet) for reading arbitrarily-shaped text in real-time. The PGNet is a single-shot text spotter, where the pixel-level character classification map is learned with proposed PG-CTC "},"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":"2104.05458","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T13:27:34Z","cross_cats_sorted":[],"title_canon_sha256":"2cf280a8244479e3bd777244d7f0d933b91a9d64d59fd6c8cffeb8ac9c7aa709","abstract_canon_sha256":"dd47bf4b8cdc145a6604af4e7b0d4c6b7fe7febe17b0e304ff380f018238f13e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:12.777565Z","signature_b64":"2HhNWpQ9cpepvyo3hyO7GzhjEq00TZz8vjekvPN+SIGq0V5uyzAdgJG9GVaxZaoiBZJZoXJqEqzzjgRBFoefAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29a07d85c6be46f8d93678e718a9febf29435f1f2100265b6c306eee805fafbb","last_reissued_at":"2026-07-05T02:31:12.777068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:12.777068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengquan Zhang, Errui Ding, Fei Qi, Guangming Shi, Jingtuo Liu, Junyu Han, Pengfei Wang, Pengyuan Lyu, Shanshan Liu, Xiaoqiang Zhang","submitted_at":"2021-04-12T13:27:34Z","abstract_excerpt":"The reading of arbitrarily-shaped text has received increasing research attention. However, existing text spotters are mostly built on two-stage frameworks or character-based methods, which suffer from either Non-Maximum Suppression (NMS), Region-of-Interest (RoI) operations, or character-level annotations. In this paper, to address the above problems, we propose a novel fully convolutional Point Gathering Network (PGNet) for reading arbitrarily-shaped text in real-time. The PGNet is a single-shot text spotter, where the pixel-level character classification map is learned with proposed PG-CTC "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05458","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/2104.05458/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":"2104.05458","created_at":"2026-07-05T02:31:12.777128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05458v1","created_at":"2026-07-05T02:31:12.777128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05458","created_at":"2026-07-05T02:31:12.777128+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGQH3BOGXZDP","created_at":"2026-07-05T02:31:12.777128+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGQH3BOGXZDPRWJW","created_at":"2026-07-05T02:31:12.777128+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGQH3BOG","created_at":"2026-07-05T02:31:12.777128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18173","citing_title":"Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FGQH3BOGXZDPRWJWPDTRRKP6X4","json":"https://pith.science/pith/FGQH3BOGXZDPRWJWPDTRRKP6X4.json","graph_json":"https://pith.science/api/pith-number/FGQH3BOGXZDPRWJWPDTRRKP6X4/graph.json","events_json":"https://pith.science/api/pith-number/FGQH3BOGXZDPRWJWPDTRRKP6X4/events.json","paper":"https://pith.science/paper/FGQH3BOG"},"agent_actions":{"view_html":"https://pith.science/pith/FGQH3BOGXZDPRWJWPDTRRKP6X4","download_json":"https://pith.science/pith/FGQH3BOGXZDPRWJWPDTRRKP6X4.json","view_paper":"https://pith.science/paper/FGQH3BOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05458&json=true","fetch_graph":"https://pith.science/api/pith-number/FGQH3BOGXZDPRWJWPDTRRKP6X4/graph.json","fetch_events":"https://pith.science/api/pith-number/FGQH3BOGXZDPRWJWPDTRRKP6X4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGQH3BOGXZDPRWJWPDTRRKP6X4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGQH3BOGXZDPRWJWPDTRRKP6X4/action/storage_attestation","attest_author":"https://pith.science/pith/FGQH3BOGXZDPRWJWPDTRRKP6X4/action/author_attestation","sign_citation":"https://pith.science/pith/FGQH3BOGXZDPRWJWPDTRRKP6X4/action/citation_signature","submit_replication":"https://pith.science/pith/FGQH3BOGXZDPRWJWPDTRRKP6X4/action/replication_record"}},"created_at":"2026-07-05T02:31:12.777128+00:00","updated_at":"2026-07-05T02:31:12.777128+00:00"}