{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2IZSRPKYJ5MYBCVBRFC26RZPQT","short_pith_number":"pith:2IZSRPKY","schema_version":"1.0","canonical_sha256":"d23328bd584f59808aa18945af472f84d23448382976b6d5a7a886ba41e00db7","source":{"kind":"arxiv","id":"2304.11431","version":1},"attestation_state":"computed","paper":{"title":"A Review of Deep Learning for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abbas Khosravi, Abduallah Mohamed, Daniel McDuff, Erik Cambria, Farhad Pourpanah, Fatih Porikli, Meenakshi Kollati, Mohammad Ghavamzadeh, Moloud Abdar, Shuicheng Yan, Swaraja Kuraparthi","submitted_at":"2023-04-22T15:30:54Z","abstract_excerpt":"Video captioning (VC) is a fast-moving, cross-disciplinary area of research that bridges work in the fields of computer vision, natural language processing (NLP), linguistics, and human-computer interaction. In essence, VC involves understanding a video and describing it with language. Captioning is used in a host of applications from creating more accessible interfaces (e.g., low-vision navigation) to video question answering (V-QA), video retrieval and content generation. This survey covers deep learning-based VC, including but, not limited to, attention-based architectures, graph networks, "},"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":"2304.11431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-22T15:30:54Z","cross_cats_sorted":[],"title_canon_sha256":"3ee017f47af96d191717a8362669a250a911a3ac4381297f529b751de608c896","abstract_canon_sha256":"d2788eaa1ec8583307202050861ee203686d2b36d569a506f45dc01439dde3f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:32.643670Z","signature_b64":"J2ZbzHRPSxDRkgQeTdqUdbaaxlW0tqr1Cly3tPubW5QxQB21W7t6V2gB3MIL9ZeVJF+1GeEkSwnmQpkNWunbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d23328bd584f59808aa18945af472f84d23448382976b6d5a7a886ba41e00db7","last_reissued_at":"2026-07-05T06:03:32.643234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:32.643234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Review of Deep Learning for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abbas Khosravi, Abduallah Mohamed, Daniel McDuff, Erik Cambria, Farhad Pourpanah, Fatih Porikli, Meenakshi Kollati, Mohammad Ghavamzadeh, Moloud Abdar, Shuicheng Yan, Swaraja Kuraparthi","submitted_at":"2023-04-22T15:30:54Z","abstract_excerpt":"Video captioning (VC) is a fast-moving, cross-disciplinary area of research that bridges work in the fields of computer vision, natural language processing (NLP), linguistics, and human-computer interaction. In essence, VC involves understanding a video and describing it with language. Captioning is used in a host of applications from creating more accessible interfaces (e.g., low-vision navigation) to video question answering (V-QA), video retrieval and content generation. This survey covers deep learning-based VC, including but, not limited to, attention-based architectures, graph networks, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11431","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/2304.11431/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":"2304.11431","created_at":"2026-07-05T06:03:32.643338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11431v1","created_at":"2026-07-05T06:03:32.643338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11431","created_at":"2026-07-05T06:03:32.643338+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IZSRPKYJ5MY","created_at":"2026-07-05T06:03:32.643338+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IZSRPKYJ5MYBCVB","created_at":"2026-07-05T06:03:32.643338+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IZSRPKY","created_at":"2026-07-05T06:03:32.643338+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/2IZSRPKYJ5MYBCVBRFC26RZPQT","json":"https://pith.science/pith/2IZSRPKYJ5MYBCVBRFC26RZPQT.json","graph_json":"https://pith.science/api/pith-number/2IZSRPKYJ5MYBCVBRFC26RZPQT/graph.json","events_json":"https://pith.science/api/pith-number/2IZSRPKYJ5MYBCVBRFC26RZPQT/events.json","paper":"https://pith.science/paper/2IZSRPKY"},"agent_actions":{"view_html":"https://pith.science/pith/2IZSRPKYJ5MYBCVBRFC26RZPQT","download_json":"https://pith.science/pith/2IZSRPKYJ5MYBCVBRFC26RZPQT.json","view_paper":"https://pith.science/paper/2IZSRPKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11431&json=true","fetch_graph":"https://pith.science/api/pith-number/2IZSRPKYJ5MYBCVBRFC26RZPQT/graph.json","fetch_events":"https://pith.science/api/pith-number/2IZSRPKYJ5MYBCVBRFC26RZPQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IZSRPKYJ5MYBCVBRFC26RZPQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IZSRPKYJ5MYBCVBRFC26RZPQT/action/storage_attestation","attest_author":"https://pith.science/pith/2IZSRPKYJ5MYBCVBRFC26RZPQT/action/author_attestation","sign_citation":"https://pith.science/pith/2IZSRPKYJ5MYBCVBRFC26RZPQT/action/citation_signature","submit_replication":"https://pith.science/pith/2IZSRPKYJ5MYBCVBRFC26RZPQT/action/replication_record"}},"created_at":"2026-07-05T06:03:32.643338+00:00","updated_at":"2026-07-05T06:03:32.643338+00:00"}