{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:LCJZUA4ZGRJDVUEGEMWBGD2GVI","short_pith_number":"pith:LCJZUA4Z","schema_version":"1.0","canonical_sha256":"58939a039934523ad086232c130f46aa332e6407c1fa91532e6163270db4336f","source":{"kind":"arxiv","id":"1505.00487","version":3},"attestation_state":"computed","paper":{"title":"Sequence to Sequence -- Video to Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeff Donahue, Kate Saenko, Marcus Rohrbach, Raymond Mooney, Subhashini Venugopalan, Trevor Darrell","submitted_at":"2015-05-03T22:32:00Z","abstract_excerpt":"Real-world videos often have complex dynamics; and methods for generating open-domain video descriptions should be sensitive to temporal structure and allow both input (sequence of frames) and output (sequence of words) of variable length. To approach this problem, we propose a novel end-to-end sequence-to-sequence model to generate captions for videos. For this we exploit recurrent neural networks, specifically LSTMs, which have demonstrated state-of-the-art performance in image caption generation. Our LSTM model is trained on video-sentence pairs and learns to associate a sequence of video f"},"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":"1505.00487","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-03T22:32:00Z","cross_cats_sorted":[],"title_canon_sha256":"75d711914949fdbe196a72fde1755609f6fbda694d397506bb93b37eb2be79fa","abstract_canon_sha256":"962703a4d8ff9bb34f2f781dfb970266524903e4a7d24d23bd9da7965688f0c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:29:54.273960Z","signature_b64":"U+TuAOboqXWqdEFiX4N0M92KGOjYF4GnZeZuWCzO0oz0qWvuaCcSMZCtOG9k8BD+hTWFJjWYozWf9rANKR/qDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58939a039934523ad086232c130f46aa332e6407c1fa91532e6163270db4336f","last_reissued_at":"2026-05-18T01:29:54.273477Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:29:54.273477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequence to Sequence -- Video to Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeff Donahue, Kate Saenko, Marcus Rohrbach, Raymond Mooney, Subhashini Venugopalan, Trevor Darrell","submitted_at":"2015-05-03T22:32:00Z","abstract_excerpt":"Real-world videos often have complex dynamics; and methods for generating open-domain video descriptions should be sensitive to temporal structure and allow both input (sequence of frames) and output (sequence of words) of variable length. To approach this problem, we propose a novel end-to-end sequence-to-sequence model to generate captions for videos. For this we exploit recurrent neural networks, specifically LSTMs, which have demonstrated state-of-the-art performance in image caption generation. Our LSTM model is trained on video-sentence pairs and learns to associate a sequence of video f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.00487","kind":"arxiv","version":3},"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":"1505.00487","created_at":"2026-05-18T01:29:54.273556+00:00"},{"alias_kind":"arxiv_version","alias_value":"1505.00487v3","created_at":"2026-05-18T01:29:54.273556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.00487","created_at":"2026-05-18T01:29:54.273556+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCJZUA4ZGRJD","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCJZUA4ZGRJDVUEG","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCJZUA4Z","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/LCJZUA4ZGRJDVUEGEMWBGD2GVI","json":"https://pith.science/pith/LCJZUA4ZGRJDVUEGEMWBGD2GVI.json","graph_json":"https://pith.science/api/pith-number/LCJZUA4ZGRJDVUEGEMWBGD2GVI/graph.json","events_json":"https://pith.science/api/pith-number/LCJZUA4ZGRJDVUEGEMWBGD2GVI/events.json","paper":"https://pith.science/paper/LCJZUA4Z"},"agent_actions":{"view_html":"https://pith.science/pith/LCJZUA4ZGRJDVUEGEMWBGD2GVI","download_json":"https://pith.science/pith/LCJZUA4ZGRJDVUEGEMWBGD2GVI.json","view_paper":"https://pith.science/paper/LCJZUA4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1505.00487&json=true","fetch_graph":"https://pith.science/api/pith-number/LCJZUA4ZGRJDVUEGEMWBGD2GVI/graph.json","fetch_events":"https://pith.science/api/pith-number/LCJZUA4ZGRJDVUEGEMWBGD2GVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCJZUA4ZGRJDVUEGEMWBGD2GVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCJZUA4ZGRJDVUEGEMWBGD2GVI/action/storage_attestation","attest_author":"https://pith.science/pith/LCJZUA4ZGRJDVUEGEMWBGD2GVI/action/author_attestation","sign_citation":"https://pith.science/pith/LCJZUA4ZGRJDVUEGEMWBGD2GVI/action/citation_signature","submit_replication":"https://pith.science/pith/LCJZUA4ZGRJDVUEGEMWBGD2GVI/action/replication_record"}},"created_at":"2026-05-18T01:29:54.273556+00:00","updated_at":"2026-05-18T01:29:54.273556+00:00"}