{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U7T2JKTPOJKIPEGA2JAMWO7SLO","short_pith_number":"pith:U7T2JKTP","schema_version":"1.0","canonical_sha256":"a7e7a4aa6f72548790c0d240cb3bf25ba39a7c9ae157b743a9b96b622a1c35be","source":{"kind":"arxiv","id":"2311.00298","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Study of Frame Selection for Text-to-Video Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Liqiang Nie, Mengxia Wu, Min Cao, Min Zhang, Yang Bai, Ziyin Zeng","submitted_at":"2023-11-01T05:03:48Z","abstract_excerpt":"Text-to-video retrieval (TVR) aims to find the most relevant video in a large video gallery given a query text. The intricate and abundant context of the video challenges the performance and efficiency of TVR. To handle the serialized video contexts, existing methods typically select a subset of frames within a video to represent the video content for TVR. How to select the most representative frames is a crucial issue, whereby the selected frames are required to not only retain the semantic information of the video but also promote retrieval efficiency by excluding temporally redundant frames"},"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":"2311.00298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T05:03:48Z","cross_cats_sorted":[],"title_canon_sha256":"487aa30a04b246f3ba6d4331078cbac637fac5b860cdc27f315284523b70f131","abstract_canon_sha256":"f49fc8905fac35a850355a2b40e02daea5f6866ce784f46a11adf4d904c16762"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:45.211645Z","signature_b64":"KAwM0ynP9wJH3FuIUZ+polfTn+evsCyFBsItfxz4kWSwVMRwWSNLQ/oByPJ2eN58ppDEjuivAAW1h19FtyUKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7e7a4aa6f72548790c0d240cb3bf25ba39a7c9ae157b743a9b96b622a1c35be","last_reissued_at":"2026-07-05T07:07:45.211207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:45.211207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study of Frame Selection for Text-to-Video Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Liqiang Nie, Mengxia Wu, Min Cao, Min Zhang, Yang Bai, Ziyin Zeng","submitted_at":"2023-11-01T05:03:48Z","abstract_excerpt":"Text-to-video retrieval (TVR) aims to find the most relevant video in a large video gallery given a query text. The intricate and abundant context of the video challenges the performance and efficiency of TVR. To handle the serialized video contexts, existing methods typically select a subset of frames within a video to represent the video content for TVR. How to select the most representative frames is a crucial issue, whereby the selected frames are required to not only retain the semantic information of the video but also promote retrieval efficiency by excluding temporally redundant frames"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00298","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.00298/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":"2311.00298","created_at":"2026-07-05T07:07:45.211263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00298v1","created_at":"2026-07-05T07:07:45.211263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00298","created_at":"2026-07-05T07:07:45.211263+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7T2JKTPOJKI","created_at":"2026-07-05T07:07:45.211263+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7T2JKTPOJKIPEGA","created_at":"2026-07-05T07:07:45.211263+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7T2JKTP","created_at":"2026-07-05T07:07:45.211263+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/U7T2JKTPOJKIPEGA2JAMWO7SLO","json":"https://pith.science/pith/U7T2JKTPOJKIPEGA2JAMWO7SLO.json","graph_json":"https://pith.science/api/pith-number/U7T2JKTPOJKIPEGA2JAMWO7SLO/graph.json","events_json":"https://pith.science/api/pith-number/U7T2JKTPOJKIPEGA2JAMWO7SLO/events.json","paper":"https://pith.science/paper/U7T2JKTP"},"agent_actions":{"view_html":"https://pith.science/pith/U7T2JKTPOJKIPEGA2JAMWO7SLO","download_json":"https://pith.science/pith/U7T2JKTPOJKIPEGA2JAMWO7SLO.json","view_paper":"https://pith.science/paper/U7T2JKTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00298&json=true","fetch_graph":"https://pith.science/api/pith-number/U7T2JKTPOJKIPEGA2JAMWO7SLO/graph.json","fetch_events":"https://pith.science/api/pith-number/U7T2JKTPOJKIPEGA2JAMWO7SLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7T2JKTPOJKIPEGA2JAMWO7SLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7T2JKTPOJKIPEGA2JAMWO7SLO/action/storage_attestation","attest_author":"https://pith.science/pith/U7T2JKTPOJKIPEGA2JAMWO7SLO/action/author_attestation","sign_citation":"https://pith.science/pith/U7T2JKTPOJKIPEGA2JAMWO7SLO/action/citation_signature","submit_replication":"https://pith.science/pith/U7T2JKTPOJKIPEGA2JAMWO7SLO/action/replication_record"}},"created_at":"2026-07-05T07:07:45.211263+00:00","updated_at":"2026-07-05T07:07:45.211263+00:00"}