{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y7PLKJYHRVPF7MMIEW2B5XF3BO","short_pith_number":"pith:Y7PLKJYH","schema_version":"1.0","canonical_sha256":"c7deb527078d5e5fb18825b41edcbb0b845fa01ff534a84c799430e1d42fc63a","source":{"kind":"arxiv","id":"1804.02516","version":2},"attestation_state":"computed","paper":{"title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoine Miech, Ivan Laptev, Josef Sivic","submitted_at":"2018-04-07T06:59:45Z","abstract_excerpt":"Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One difficulty with this approach, however, is the lack of large-scale annotated video-caption datasets for training. To address this issue, we aim at learning text-video embeddings from heterogeneous data sources. To this end, we propose a Mixture-of-Embedding-Experts (MEE) model with ability to handle missing input modalities during training. As a result, our framework can learn improved text-video embeddings simultaneously"},"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":"1804.02516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-07T06:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"4dee3a77d7437a4f67a7a7712effa7996785943ef3a5cea7292536d89c874804","abstract_canon_sha256":"c331e9d6000b62421b0c01fe22d1cab441c40eb0c4e0b3d3be0ccbd4f0e780c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:51.947642Z","signature_b64":"QYmNG7JUhGCpLjk5ye3rbcEamIAijxAA5EINtgktfeLICh4EnL/oPi6NFjWk+Y2IQy+zYKnhVbclsSo7RdrbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7deb527078d5e5fb18825b41edcbb0b845fa01ff534a84c799430e1d42fc63a","last_reissued_at":"2026-07-05T00:33:51.947241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:51.947241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoine Miech, Ivan Laptev, Josef Sivic","submitted_at":"2018-04-07T06:59:45Z","abstract_excerpt":"Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One difficulty with this approach, however, is the lack of large-scale annotated video-caption datasets for training. To address this issue, we aim at learning text-video embeddings from heterogeneous data sources. To this end, we propose a Mixture-of-Embedding-Experts (MEE) model with ability to handle missing input modalities during training. As a result, our framework can learn improved text-video embeddings simultaneously"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02516","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1804.02516/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1804.02516","created_at":"2026-07-05T00:33:51.947298+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.02516v2","created_at":"2026-07-05T00:33:51.947298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02516","created_at":"2026-07-05T00:33:51.947298+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7PLKJYHRVPF","created_at":"2026-07-05T00:33:51.947298+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7PLKJYHRVPF7MMI","created_at":"2026-07-05T00:33:51.947298+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7PLKJYH","created_at":"2026-07-05T00:33:51.947298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20838","citing_title":"USV: Towards Understanding the User-generated Short-form Videos","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2409.07825","citing_title":"Deep Multimodal Learning with Missing Modality: A Survey","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO","json":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO.json","graph_json":"https://pith.science/api/pith-number/Y7PLKJYHRVPF7MMIEW2B5XF3BO/graph.json","events_json":"https://pith.science/api/pith-number/Y7PLKJYHRVPF7MMIEW2B5XF3BO/events.json","paper":"https://pith.science/paper/Y7PLKJYH"},"agent_actions":{"view_html":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO","download_json":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO.json","view_paper":"https://pith.science/paper/Y7PLKJYH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.02516&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7PLKJYHRVPF7MMIEW2B5XF3BO/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7PLKJYHRVPF7MMIEW2B5XF3BO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO/action/storage_attestation","attest_author":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO/action/author_attestation","sign_citation":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO/action/citation_signature","submit_replication":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO/action/replication_record"}},"created_at":"2026-07-05T00:33:51.947298+00:00","updated_at":"2026-07-05T00:33:51.947298+00:00"}