{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:LZVWYV7LOQ6EC7HKVBCARIVPA3","short_pith_number":"pith:LZVWYV7L","schema_version":"1.0","canonical_sha256":"5e6b6c57eb743c417ceaa84408a2af06e420ae2ae13ce503d50aa424f8d03aa2","source":{"kind":"arxiv","id":"1510.07712","version":2},"attestation_state":"computed","paper":{"title":"Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haonan Yu, Jiang Wang, Wei Xu, Yi Yang, Zhiheng Huang","submitted_at":"2015-10-26T22:47:00Z","abstract_excerpt":"We present an approach that exploits hierarchical Recurrent Neural Networks (RNNs) to tackle the video captioning problem, i.e., generating one or multiple sentences to describe a realistic video. Our hierarchical framework contains a sentence generator and a paragraph generator. The sentence generator produces one simple short sentence that describes a specific short video interval. It exploits both temporal- and spatial-attention mechanisms to selectively focus on visual elements during generation. The paragraph generator captures the inter-sentence dependency by taking as input the sententi"},"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":"1510.07712","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-10-26T22:47:00Z","cross_cats_sorted":[],"title_canon_sha256":"b7ef89a0c989b6415d56b3d178229e96c2256057f6af475fa57ba8a9e51baa36","abstract_canon_sha256":"7cedd094d8df8cb1c2f751e3530c847e419eb92b017b3bc05eb960ff2f1a2f2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:37.128154Z","signature_b64":"lKkoImLpVkp5knPJAqvdhA2BAZa+dw3gjxJPOY3fD9zyDUbL+VAhiEaU8t5xyBMkuqay76/0PhAJk6Nmwi/9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e6b6c57eb743c417ceaa84408a2af06e420ae2ae13ce503d50aa424f8d03aa2","last_reissued_at":"2026-05-18T01:17:37.127457Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:37.127457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haonan Yu, Jiang Wang, Wei Xu, Yi Yang, Zhiheng Huang","submitted_at":"2015-10-26T22:47:00Z","abstract_excerpt":"We present an approach that exploits hierarchical Recurrent Neural Networks (RNNs) to tackle the video captioning problem, i.e., generating one or multiple sentences to describe a realistic video. Our hierarchical framework contains a sentence generator and a paragraph generator. The sentence generator produces one simple short sentence that describes a specific short video interval. It exploits both temporal- and spatial-attention mechanisms to selectively focus on visual elements during generation. The paragraph generator captures the inter-sentence dependency by taking as input the sententi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.07712","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":""},"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":"1510.07712","created_at":"2026-05-18T01:17:37.127570+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.07712v2","created_at":"2026-05-18T01:17:37.127570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.07712","created_at":"2026-05-18T01:17:37.127570+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZVWYV7LOQ6E","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZVWYV7LOQ6EC7HK","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZVWYV7L","created_at":"2026-05-18T12:29:29.992203+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/LZVWYV7LOQ6EC7HKVBCARIVPA3","json":"https://pith.science/pith/LZVWYV7LOQ6EC7HKVBCARIVPA3.json","graph_json":"https://pith.science/api/pith-number/LZVWYV7LOQ6EC7HKVBCARIVPA3/graph.json","events_json":"https://pith.science/api/pith-number/LZVWYV7LOQ6EC7HKVBCARIVPA3/events.json","paper":"https://pith.science/paper/LZVWYV7L"},"agent_actions":{"view_html":"https://pith.science/pith/LZVWYV7LOQ6EC7HKVBCARIVPA3","download_json":"https://pith.science/pith/LZVWYV7LOQ6EC7HKVBCARIVPA3.json","view_paper":"https://pith.science/paper/LZVWYV7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.07712&json=true","fetch_graph":"https://pith.science/api/pith-number/LZVWYV7LOQ6EC7HKVBCARIVPA3/graph.json","fetch_events":"https://pith.science/api/pith-number/LZVWYV7LOQ6EC7HKVBCARIVPA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZVWYV7LOQ6EC7HKVBCARIVPA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZVWYV7LOQ6EC7HKVBCARIVPA3/action/storage_attestation","attest_author":"https://pith.science/pith/LZVWYV7LOQ6EC7HKVBCARIVPA3/action/author_attestation","sign_citation":"https://pith.science/pith/LZVWYV7LOQ6EC7HKVBCARIVPA3/action/citation_signature","submit_replication":"https://pith.science/pith/LZVWYV7LOQ6EC7HKVBCARIVPA3/action/replication_record"}},"created_at":"2026-05-18T01:17:37.127570+00:00","updated_at":"2026-05-18T01:17:37.127570+00:00"}