{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:I5GWQTTYWZE6RACSX5LHA6IPDR","short_pith_number":"pith:I5GWQTTY","schema_version":"1.0","canonical_sha256":"474d684e78b649e88052bf5670790f1c4bc384204d89446e702e160daa48fdfc","source":{"kind":"arxiv","id":"1702.01528","version":3},"attestation_state":"computed","paper":{"title":"Contextually Customized Video Summaries via Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"In So Kweon, Jinsoo Choi, Tae-Hyun Oh","submitted_at":"2017-02-06T08:31:44Z","abstract_excerpt":"The best summary of a long video differs among different people due to its highly subjective nature. Even for the same person, the best summary may change with time or mood. In this paper, we introduce the task of generating customized video summaries through simple text. First, we train a deep architecture to effectively learn semantic embeddings of video frames by leveraging the abundance of image-caption data via a progressive and residual manner. Given a user-specific text description, our algorithm is able to select semantically relevant video segments and produce a temporally aligned vid"},"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":"1702.01528","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-06T08:31:44Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"6b7b45a03a1e5a93f5fb2ec502f06b52cc4b0c884bd32bf9f241088a5f4ec3b7","abstract_canon_sha256":"e06c8852200eb5ade560f108c648289d19e9b7a05f08ae2982c1c067f00a2fb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:11.128845Z","signature_b64":"0VwJBrRYf0kvdXowI6NFUuw0erj7vrL9n9R8D5SItlVXcSporgUefEf+LlCsRAIAp3kyZVpjmxJX15jagO9rDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"474d684e78b649e88052bf5670790f1c4bc384204d89446e702e160daa48fdfc","last_reissued_at":"2026-05-18T00:22:11.128435Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:11.128435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextually Customized Video Summaries via Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"In So Kweon, Jinsoo Choi, Tae-Hyun Oh","submitted_at":"2017-02-06T08:31:44Z","abstract_excerpt":"The best summary of a long video differs among different people due to its highly subjective nature. Even for the same person, the best summary may change with time or mood. In this paper, we introduce the task of generating customized video summaries through simple text. First, we train a deep architecture to effectively learn semantic embeddings of video frames by leveraging the abundance of image-caption data via a progressive and residual manner. Given a user-specific text description, our algorithm is able to select semantically relevant video segments and produce a temporally aligned vid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01528","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":"1702.01528","created_at":"2026-05-18T00:22:11.128494+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.01528v3","created_at":"2026-05-18T00:22:11.128494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01528","created_at":"2026-05-18T00:22:11.128494+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5GWQTTYWZE6","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5GWQTTYWZE6RACS","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5GWQTTY","created_at":"2026-05-18T12:31:21.493067+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/I5GWQTTYWZE6RACSX5LHA6IPDR","json":"https://pith.science/pith/I5GWQTTYWZE6RACSX5LHA6IPDR.json","graph_json":"https://pith.science/api/pith-number/I5GWQTTYWZE6RACSX5LHA6IPDR/graph.json","events_json":"https://pith.science/api/pith-number/I5GWQTTYWZE6RACSX5LHA6IPDR/events.json","paper":"https://pith.science/paper/I5GWQTTY"},"agent_actions":{"view_html":"https://pith.science/pith/I5GWQTTYWZE6RACSX5LHA6IPDR","download_json":"https://pith.science/pith/I5GWQTTYWZE6RACSX5LHA6IPDR.json","view_paper":"https://pith.science/paper/I5GWQTTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.01528&json=true","fetch_graph":"https://pith.science/api/pith-number/I5GWQTTYWZE6RACSX5LHA6IPDR/graph.json","fetch_events":"https://pith.science/api/pith-number/I5GWQTTYWZE6RACSX5LHA6IPDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5GWQTTYWZE6RACSX5LHA6IPDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5GWQTTYWZE6RACSX5LHA6IPDR/action/storage_attestation","attest_author":"https://pith.science/pith/I5GWQTTYWZE6RACSX5LHA6IPDR/action/author_attestation","sign_citation":"https://pith.science/pith/I5GWQTTYWZE6RACSX5LHA6IPDR/action/citation_signature","submit_replication":"https://pith.science/pith/I5GWQTTYWZE6RACSX5LHA6IPDR/action/replication_record"}},"created_at":"2026-05-18T00:22:11.128494+00:00","updated_at":"2026-05-18T00:22:11.128494+00:00"}