{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FDBBIDFAVDBI3WYVJCCJL4YRFE","short_pith_number":"pith:FDBBIDFA","schema_version":"1.0","canonical_sha256":"28c2140ca0a8c28ddb15488495f311291d8d2235ae9711321064bfd8eb20b7db","source":{"kind":"arxiv","id":"2303.14829","version":2},"attestation_state":"computed","paper":{"title":"SEM-POS: Grammatically and Semantically Correct Video Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian Hilton, Armin Mustafa, Asmar Nadeem, Graham Thomas, Robert Dawes","submitted_at":"2023-03-26T21:42:40Z","abstract_excerpt":"Generating grammatically and semantically correct captions in video captioning is a challenging task. The captions generated from the existing methods are either word-by-word that do not align with grammatical structure or miss key information from the input videos. To address these issues, we introduce a novel global-local fusion network, with a Global-Local Fusion Block (GLFB) that encodes and fuses features from different parts of speech (POS) components with visual-spatial features. We use novel combinations of different POS components - 'determinant + subject', 'auxiliary verb', 'verb', a"},"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":"2303.14829","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-26T21:42:40Z","cross_cats_sorted":[],"title_canon_sha256":"58f0b2eff84d792a6db57ffa9b134b606fbce94aca5bd4d35a2c2628ee829048","abstract_canon_sha256":"2208f780574a3c8c3ac81e50377f55cb128520a248c60a56c94968c790950463"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:49.061904Z","signature_b64":"IXz1CnKrMQnuP/AQRw5KJte0908/TKE8QZtBD4K+NKJpeZDzAmmC8BtsK3UnupFeuGFGUzpjKZvfZ3Gt2umuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28c2140ca0a8c28ddb15488495f311291d8d2235ae9711321064bfd8eb20b7db","last_reissued_at":"2026-07-05T06:17:49.061484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:49.061484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEM-POS: Grammatically and Semantically Correct Video Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian Hilton, Armin Mustafa, Asmar Nadeem, Graham Thomas, Robert Dawes","submitted_at":"2023-03-26T21:42:40Z","abstract_excerpt":"Generating grammatically and semantically correct captions in video captioning is a challenging task. The captions generated from the existing methods are either word-by-word that do not align with grammatical structure or miss key information from the input videos. To address these issues, we introduce a novel global-local fusion network, with a Global-Local Fusion Block (GLFB) that encodes and fuses features from different parts of speech (POS) components with visual-spatial features. We use novel combinations of different POS components - 'determinant + subject', 'auxiliary verb', 'verb', a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14829","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/2303.14829/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":"2303.14829","created_at":"2026-07-05T06:17:49.061540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14829v2","created_at":"2026-07-05T06:17:49.061540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14829","created_at":"2026-07-05T06:17:49.061540+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDBBIDFAVDBI","created_at":"2026-07-05T06:17:49.061540+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDBBIDFAVDBI3WYV","created_at":"2026-07-05T06:17:49.061540+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDBBIDFA","created_at":"2026-07-05T06:17:49.061540+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/FDBBIDFAVDBI3WYVJCCJL4YRFE","json":"https://pith.science/pith/FDBBIDFAVDBI3WYVJCCJL4YRFE.json","graph_json":"https://pith.science/api/pith-number/FDBBIDFAVDBI3WYVJCCJL4YRFE/graph.json","events_json":"https://pith.science/api/pith-number/FDBBIDFAVDBI3WYVJCCJL4YRFE/events.json","paper":"https://pith.science/paper/FDBBIDFA"},"agent_actions":{"view_html":"https://pith.science/pith/FDBBIDFAVDBI3WYVJCCJL4YRFE","download_json":"https://pith.science/pith/FDBBIDFAVDBI3WYVJCCJL4YRFE.json","view_paper":"https://pith.science/paper/FDBBIDFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14829&json=true","fetch_graph":"https://pith.science/api/pith-number/FDBBIDFAVDBI3WYVJCCJL4YRFE/graph.json","fetch_events":"https://pith.science/api/pith-number/FDBBIDFAVDBI3WYVJCCJL4YRFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDBBIDFAVDBI3WYVJCCJL4YRFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDBBIDFAVDBI3WYVJCCJL4YRFE/action/storage_attestation","attest_author":"https://pith.science/pith/FDBBIDFAVDBI3WYVJCCJL4YRFE/action/author_attestation","sign_citation":"https://pith.science/pith/FDBBIDFAVDBI3WYVJCCJL4YRFE/action/citation_signature","submit_replication":"https://pith.science/pith/FDBBIDFAVDBI3WYVJCCJL4YRFE/action/replication_record"}},"created_at":"2026-07-05T06:17:49.061540+00:00","updated_at":"2026-07-05T06:17:49.061540+00:00"}