{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:YQWVR77TXRSFDVDI7BEZLW6CPT","short_pith_number":"pith:YQWVR77T","schema_version":"1.0","canonical_sha256":"c42d58fff3bc6451d468f84995dbc27cf0839e4583e21f1e96d135f8f774312f","source":{"kind":"arxiv","id":"1609.08124","version":1},"attestation_state":"computed","paper":{"title":"Learning Language-Visual Embedding for Movie Understanding with Natural-Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Atousa Torabi, Leonid Sigal, Niket Tandon","submitted_at":"2016-09-26T19:14:12Z","abstract_excerpt":"Learning a joint language-visual embedding has a number of very appealing properties and can result in variety of practical application, including natural language image/video annotation and search. In this work, we study three different joint language-visual neural network model architectures. We evaluate our models on large scale LSMDC16 movie dataset for two tasks: 1) Standard Ranking for video annotation and retrieval 2) Our proposed movie multiple-choice test. This test facilitate automatic evaluation of visual-language models for natural language video annotation based on human activitie"},"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":"1609.08124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-26T19:14:12Z","cross_cats_sorted":[],"title_canon_sha256":"35157ed78949456049774293f59578c7e3de3b7eb1c6c043a7f1c895e9a75801","abstract_canon_sha256":"01de924187bf024b59bf774c1672994a6543c0a6717e04686826c7dade9b6af7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:54.370751Z","signature_b64":"R+89doHTjWWBtFAD/48QXZTLN1pANQvy7Uid/P1CVjckh5isUNNV7I7h3JOTMonS41m287snb82q5vqUrhSTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c42d58fff3bc6451d468f84995dbc27cf0839e4583e21f1e96d135f8f774312f","last_reissued_at":"2026-05-18T01:03:54.370117Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:54.370117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Language-Visual Embedding for Movie Understanding with Natural-Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Atousa Torabi, Leonid Sigal, Niket Tandon","submitted_at":"2016-09-26T19:14:12Z","abstract_excerpt":"Learning a joint language-visual embedding has a number of very appealing properties and can result in variety of practical application, including natural language image/video annotation and search. In this work, we study three different joint language-visual neural network model architectures. We evaluate our models on large scale LSMDC16 movie dataset for two tasks: 1) Standard Ranking for video annotation and retrieval 2) Our proposed movie multiple-choice test. This test facilitate automatic evaluation of visual-language models for natural language video annotation based on human activitie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.08124","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":"1609.08124","created_at":"2026-05-18T01:03:54.370233+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.08124v1","created_at":"2026-05-18T01:03:54.370233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.08124","created_at":"2026-05-18T01:03:54.370233+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQWVR77TXRSF","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQWVR77TXRSFDVDI","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQWVR77T","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.20838","citing_title":"USV: Towards Understanding the User-generated Short-form Videos","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16671","citing_title":"Demystifying CLIP Data","ref_index":140,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT","json":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT.json","graph_json":"https://pith.science/api/pith-number/YQWVR77TXRSFDVDI7BEZLW6CPT/graph.json","events_json":"https://pith.science/api/pith-number/YQWVR77TXRSFDVDI7BEZLW6CPT/events.json","paper":"https://pith.science/paper/YQWVR77T"},"agent_actions":{"view_html":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT","download_json":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT.json","view_paper":"https://pith.science/paper/YQWVR77T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.08124&json=true","fetch_graph":"https://pith.science/api/pith-number/YQWVR77TXRSFDVDI7BEZLW6CPT/graph.json","fetch_events":"https://pith.science/api/pith-number/YQWVR77TXRSFDVDI7BEZLW6CPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT/action/storage_attestation","attest_author":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT/action/author_attestation","sign_citation":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT/action/citation_signature","submit_replication":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT/action/replication_record"}},"created_at":"2026-05-18T01:03:54.370233+00:00","updated_at":"2026-05-18T01:03:54.370233+00:00"}