{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TBJA2UN5OC62XPW3DYP4DOH6WJ","short_pith_number":"pith:TBJA2UN5","schema_version":"1.0","canonical_sha256":"98520d51bd70bdabbedb1e1fc1b8feb270db8b77286243b504b363d07c8b9723","source":{"kind":"arxiv","id":"2009.05381","version":2},"attestation_state":"computed","paper":{"title":"Dual Encoding for Video Retrieval by Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chaoxi Xu, Gang Yang, Jianfeng Dong, Meng Wang, Xirong Li, Xun Wang, Xun Yang","submitted_at":"2020-09-10T15:49:39Z","abstract_excerpt":"This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of a natural-language sentence, with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is crucial. To that end, the two modalities need to be first encoded into real-valued vectors and then projected into a common space. In this paper we achieve this by proposing a dual deep encoding network that enc"},"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":"2009.05381","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-10T15:49:39Z","cross_cats_sorted":["cs.IR","cs.MM"],"title_canon_sha256":"076b0b2749bb9c03aa9925e72d242df942b194f322602574f9530619f8714f85","abstract_canon_sha256":"d1f7bdf50c4db8e97a33618bf3eef662f9902fdfe6c6a93617a95919e4e814d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:15.111830Z","signature_b64":"/QYgZxrdynxUM/Gs+e9kmK5+/24E6UBUg9O+UM6jrpFJO4D59BU3Wf3TbCJ6Pr2CcFCK+pPMEtuwOtpmUQgPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98520d51bd70bdabbedb1e1fc1b8feb270db8b77286243b504b363d07c8b9723","last_reissued_at":"2026-07-05T02:16:15.111068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:15.111068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Encoding for Video Retrieval by Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chaoxi Xu, Gang Yang, Jianfeng Dong, Meng Wang, Xirong Li, Xun Wang, Xun Yang","submitted_at":"2020-09-10T15:49:39Z","abstract_excerpt":"This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of a natural-language sentence, with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is crucial. To that end, the two modalities need to be first encoded into real-valued vectors and then projected into a common space. In this paper we achieve this by proposing a dual deep encoding network that enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.05381","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/2009.05381/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":"2009.05381","created_at":"2026-07-05T02:16:15.111166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.05381v2","created_at":"2026-07-05T02:16:15.111166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.05381","created_at":"2026-07-05T02:16:15.111166+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBJA2UN5OC62","created_at":"2026-07-05T02:16:15.111166+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBJA2UN5OC62XPW3","created_at":"2026-07-05T02:16:15.111166+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBJA2UN5","created_at":"2026-07-05T02:16:15.111166+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/TBJA2UN5OC62XPW3DYP4DOH6WJ","json":"https://pith.science/pith/TBJA2UN5OC62XPW3DYP4DOH6WJ.json","graph_json":"https://pith.science/api/pith-number/TBJA2UN5OC62XPW3DYP4DOH6WJ/graph.json","events_json":"https://pith.science/api/pith-number/TBJA2UN5OC62XPW3DYP4DOH6WJ/events.json","paper":"https://pith.science/paper/TBJA2UN5"},"agent_actions":{"view_html":"https://pith.science/pith/TBJA2UN5OC62XPW3DYP4DOH6WJ","download_json":"https://pith.science/pith/TBJA2UN5OC62XPW3DYP4DOH6WJ.json","view_paper":"https://pith.science/paper/TBJA2UN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.05381&json=true","fetch_graph":"https://pith.science/api/pith-number/TBJA2UN5OC62XPW3DYP4DOH6WJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TBJA2UN5OC62XPW3DYP4DOH6WJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBJA2UN5OC62XPW3DYP4DOH6WJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBJA2UN5OC62XPW3DYP4DOH6WJ/action/storage_attestation","attest_author":"https://pith.science/pith/TBJA2UN5OC62XPW3DYP4DOH6WJ/action/author_attestation","sign_citation":"https://pith.science/pith/TBJA2UN5OC62XPW3DYP4DOH6WJ/action/citation_signature","submit_replication":"https://pith.science/pith/TBJA2UN5OC62XPW3DYP4DOH6WJ/action/replication_record"}},"created_at":"2026-07-05T02:16:15.111166+00:00","updated_at":"2026-07-05T02:16:15.111166+00:00"}