{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:B5LRDKAECSWMCLWFXEKNQYVYTA","short_pith_number":"pith:B5LRDKAE","schema_version":"1.0","canonical_sha256":"0f5711a80414acc12ec5b914d862b8981ae27489ef27f1a6cf2ec176a4c4b173","source":{"kind":"arxiv","id":"1403.6173","version":1},"attestation_state":"computed","paper":{"title":"Coherent Multi-Sentence Video Description with Variable Level of Detail","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Senina, Annemarie Friedrich, Bernt Schiele, Manfred Pinkal, Marcus Rohrbach, Mykhaylo Andriluka, Sikandar Amin, Wei Qiu","submitted_at":"2014-03-24T22:28:38Z","abstract_excerpt":"Humans can easily describe what they see in a coherent way and at varying level of detail. However, existing approaches for automatic video description are mainly focused on single sentence generation and produce descriptions at a fixed level of detail. In this paper, we address both of these limitations: for a variable level of detail we produce coherent multi-sentence descriptions of complex videos. We follow a two-step approach where we first learn to predict a semantic representation (SR) from video and then generate natural language descriptions from the SR. To produce consistent multi-se"},"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":"1403.6173","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-03-24T22:28:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9efe9f71b1ddccda470c5004465c846f652180b15b619814fa5def5fa450cbfb","abstract_canon_sha256":"ab930c77cc220b89cb03fbad862150fe2f69be564db95cbe952bc20083a5161d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:04.365290Z","signature_b64":"e5lNIEQQRIVtD87g3X+3U1wHl2WhNmNXgFxct84+Kt7oRZdqYPaWSI1qoCb4rVm/MGHp9hLH5zfIy7zsDFSjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f5711a80414acc12ec5b914d862b8981ae27489ef27f1a6cf2ec176a4c4b173","last_reissued_at":"2026-05-18T01:04:04.364912Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:04.364912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coherent Multi-Sentence Video Description with Variable Level of Detail","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Senina, Annemarie Friedrich, Bernt Schiele, Manfred Pinkal, Marcus Rohrbach, Mykhaylo Andriluka, Sikandar Amin, Wei Qiu","submitted_at":"2014-03-24T22:28:38Z","abstract_excerpt":"Humans can easily describe what they see in a coherent way and at varying level of detail. However, existing approaches for automatic video description are mainly focused on single sentence generation and produce descriptions at a fixed level of detail. In this paper, we address both of these limitations: for a variable level of detail we produce coherent multi-sentence descriptions of complex videos. We follow a two-step approach where we first learn to predict a semantic representation (SR) from video and then generate natural language descriptions from the SR. To produce consistent multi-se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.6173","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":""},"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":"1403.6173","created_at":"2026-05-18T01:04:04.364969+00:00"},{"alias_kind":"arxiv_version","alias_value":"1403.6173v1","created_at":"2026-05-18T01:04:04.364969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.6173","created_at":"2026-05-18T01:04:04.364969+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5LRDKAECSWM","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5LRDKAECSWMCLWF","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5LRDKAE","created_at":"2026-05-18T12:28:22.404517+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/B5LRDKAECSWMCLWFXEKNQYVYTA","json":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA.json","graph_json":"https://pith.science/api/pith-number/B5LRDKAECSWMCLWFXEKNQYVYTA/graph.json","events_json":"https://pith.science/api/pith-number/B5LRDKAECSWMCLWFXEKNQYVYTA/events.json","paper":"https://pith.science/paper/B5LRDKAE"},"agent_actions":{"view_html":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA","download_json":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA.json","view_paper":"https://pith.science/paper/B5LRDKAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1403.6173&json=true","fetch_graph":"https://pith.science/api/pith-number/B5LRDKAECSWMCLWFXEKNQYVYTA/graph.json","fetch_events":"https://pith.science/api/pith-number/B5LRDKAECSWMCLWFXEKNQYVYTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA/action/storage_attestation","attest_author":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA/action/author_attestation","sign_citation":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA/action/citation_signature","submit_replication":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA/action/replication_record"}},"created_at":"2026-05-18T01:04:04.364969+00:00","updated_at":"2026-05-18T01:04:04.364969+00:00"}