{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2RHMPISR72DDQCFSNVBV37FCAS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d7ea2b7c67b5d5e5e098a7239aeb2797e3e3c8585cd040603c56a311b8ab80ff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-19T11:40:35Z","title_canon_sha256":"47f094981b5b67312ae6fb985f600cc7ef7384e415f70aa06502969aa2eb9739"},"schema_version":"1.0","source":{"id":"2011.09781","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.09781","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"arxiv_version","alias_value":"2011.09781v1","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09781","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_12","alias_value":"2RHMPISR72DD","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_16","alias_value":"2RHMPISR72DDQCFS","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_8","alias_value":"2RHMPISR","created_at":"2026-07-05T01:53:00Z"}],"graph_snapshots":[{"event_id":"sha256:1b8b0f04e4cf17488ced2be007441b4d8757f0840b14612c055367f457ef44ae","target":"graph","created_at":"2026-07-05T01:53:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.09781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With only bounding-box annotations in the spatial domain, existing video scene text detection (VSTD) benchmarks lack temporal relation of text instances among video frames, which hinders the development of video text-related applications. In this paper, we systematically introduce a new large-scale benchmark, named as STVText4, a well-designed spatial-temporal detection metric (STDM), and a novel clustering-based baseline method, referred to as Temporal Clustering (TC). STVText4 opens a challenging yet promising direction of VSTD, termed as ST-VSTD, which targets at simultaneously detecting vi","authors_text":"Chang Liu, Qixiang Ye, Weiqiang Wang, Yuanqiang Cai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-19T11:40:35Z","title":"Towards Spatio-Temporal Video Scene Text Detection via Temporal Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09781","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1e63f9ef338004b9da89d7b52d55ccfa5d5925074383ce367058ce627e618593","target":"record","created_at":"2026-07-05T01:53:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d7ea2b7c67b5d5e5e098a7239aeb2797e3e3c8585cd040603c56a311b8ab80ff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-19T11:40:35Z","title_canon_sha256":"47f094981b5b67312ae6fb985f600cc7ef7384e415f70aa06502969aa2eb9739"},"schema_version":"1.0","source":{"id":"2011.09781","kind":"arxiv","version":1}},"canonical_sha256":"d44ec7a251fe863808b26d435dfca204944100431e0869ebf7f6b83bb2b332d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d44ec7a251fe863808b26d435dfca204944100431e0869ebf7f6b83bb2b332d6","first_computed_at":"2026-07-05T01:53:00.714341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:00.714341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bfY0TaqmSmOkZMEVIsMrgIJKwd7xRHLaIsdlGeg3XhtTVoejITpl4xxGQMexstVQaWrYqt3FAjEz89RymgLUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:00.714734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.09781","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e63f9ef338004b9da89d7b52d55ccfa5d5925074383ce367058ce627e618593","sha256:1b8b0f04e4cf17488ced2be007441b4d8757f0840b14612c055367f457ef44ae"],"state_sha256":"f32339eb9b56c545c67dae4722f9ed14eff349258887c445184a21ca1896a50b"}