{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LRDIAXDSFHX5NDJQGG7NWCYA6P","short_pith_number":"pith:LRDIAXDS","schema_version":"1.0","canonical_sha256":"5c46805c7229efd68d3031bedb0b00f3d376bd6307e198fbabcafac672af4d0a","source":{"kind":"arxiv","id":"2207.10362","version":1},"attestation_state":"computed","paper":{"title":"LocVTP: Video-Text Pre-training for Temporal Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Jue Wang, Junwu Weng, Meng Cao, Tianyu Yang, Yuexian Zou","submitted_at":"2022-07-21T08:43:51Z","abstract_excerpt":"Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limited to retrieval-based downstream tasks, e.g., video retrieval, whereas their transfer potentials on localization-based tasks, e.g., temporal grounding, are under-explored. In this paper, we experimentally analyze and demonstrate the incompatibility of current VTP methods with localization tasks, and propose a novel Localization-oriented Video-Text Pre-training framework, dubbed as LocVTP. Specifically, we perform th"},"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":"2207.10362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-21T08:43:51Z","cross_cats_sorted":[],"title_canon_sha256":"9d5ba09834711165edbcc376c6cf88bcf5e158cc76ad109b7241deb391453537","abstract_canon_sha256":"016363b3bfce7dc3ae3b8a74677f581cee312b554e169558054ca70db22bc3fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:24.310376Z","signature_b64":"kFduTVEF3T2+bBVKvvSxGvMp2sXD9US2mO3+cdbja5hKSiPBEofQylxH7MOnFR/u0hOdRxTMZu+yR3ZJfYPCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c46805c7229efd68d3031bedb0b00f3d376bd6307e198fbabcafac672af4d0a","last_reissued_at":"2026-07-05T04:42:24.309852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:24.309852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LocVTP: Video-Text Pre-training for Temporal Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Jue Wang, Junwu Weng, Meng Cao, Tianyu Yang, Yuexian Zou","submitted_at":"2022-07-21T08:43:51Z","abstract_excerpt":"Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limited to retrieval-based downstream tasks, e.g., video retrieval, whereas their transfer potentials on localization-based tasks, e.g., temporal grounding, are under-explored. In this paper, we experimentally analyze and demonstrate the incompatibility of current VTP methods with localization tasks, and propose a novel Localization-oriented Video-Text Pre-training framework, dubbed as LocVTP. Specifically, we perform th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10362","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/2207.10362/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":"2207.10362","created_at":"2026-07-05T04:42:24.309916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.10362v1","created_at":"2026-07-05T04:42:24.309916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10362","created_at":"2026-07-05T04:42:24.309916+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRDIAXDSFHX5","created_at":"2026-07-05T04:42:24.309916+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRDIAXDSFHX5NDJQ","created_at":"2026-07-05T04:42:24.309916+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRDIAXDS","created_at":"2026-07-05T04:42:24.309916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.24124","citing_title":"Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRDIAXDSFHX5NDJQGG7NWCYA6P","json":"https://pith.science/pith/LRDIAXDSFHX5NDJQGG7NWCYA6P.json","graph_json":"https://pith.science/api/pith-number/LRDIAXDSFHX5NDJQGG7NWCYA6P/graph.json","events_json":"https://pith.science/api/pith-number/LRDIAXDSFHX5NDJQGG7NWCYA6P/events.json","paper":"https://pith.science/paper/LRDIAXDS"},"agent_actions":{"view_html":"https://pith.science/pith/LRDIAXDSFHX5NDJQGG7NWCYA6P","download_json":"https://pith.science/pith/LRDIAXDSFHX5NDJQGG7NWCYA6P.json","view_paper":"https://pith.science/paper/LRDIAXDS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.10362&json=true","fetch_graph":"https://pith.science/api/pith-number/LRDIAXDSFHX5NDJQGG7NWCYA6P/graph.json","fetch_events":"https://pith.science/api/pith-number/LRDIAXDSFHX5NDJQGG7NWCYA6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRDIAXDSFHX5NDJQGG7NWCYA6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRDIAXDSFHX5NDJQGG7NWCYA6P/action/storage_attestation","attest_author":"https://pith.science/pith/LRDIAXDSFHX5NDJQGG7NWCYA6P/action/author_attestation","sign_citation":"https://pith.science/pith/LRDIAXDSFHX5NDJQGG7NWCYA6P/action/citation_signature","submit_replication":"https://pith.science/pith/LRDIAXDSFHX5NDJQGG7NWCYA6P/action/replication_record"}},"created_at":"2026-07-05T04:42:24.309916+00:00","updated_at":"2026-07-05T04:42:24.309916+00:00"}