{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:G2BGN7ZPQPPOBIHHR4ISAMLGZM","short_pith_number":"pith:G2BGN7ZP","schema_version":"1.0","canonical_sha256":"368266ff2f83dee0a0e78f11203166cb370d9d0b6c967112a7883888ddcb756b","source":{"kind":"arxiv","id":"2209.13307","version":1},"attestation_state":"computed","paper":{"title":"Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Ancong Wu, Chengzhi Lin, Chunhua Shen, Junwei Liang, Jun Zhang, Wei-Shi Zheng, Wenhang Ge","submitted_at":"2022-09-27T11:13:48Z","abstract_excerpt":"Cross-modal retrieval between videos and texts has gained increasing research interest due to the rapid emergence of videos on the web. Generally, a video contains rich instance and event information and the query text only describes a part of the information. Thus, a video can correspond to multiple different text descriptions and queries. We call this phenomenon the ``Video-Text Correspondence Ambiguity'' problem. Current techniques mostly concentrate on mining local or multi-level alignment between contents of a video and text (\\textit{e.g.}, object to entity and action to verb). It is diff"},"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":"2209.13307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-27T11:13:48Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"b0f3d45469e33e37aa7d0248d0a57030516defbde981fa9f790b2e92cf24f839","abstract_canon_sha256":"9b5674e88dad8bad977d1596a75fadb2b61cc590b89eef5e303b4a96b75fa029"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:09.159704Z","signature_b64":"IJu4GY6P8jJ2H8lPPokw0aLpNHcQc3vF9YW9W4O06wxT739cOeXvpBFCyFNGJRrB4WSXxrULlHTXL+bugSi/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"368266ff2f83dee0a0e78f11203166cb370d9d0b6c967112a7883888ddcb756b","last_reissued_at":"2026-07-05T05:01:09.159294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:09.159294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Ancong Wu, Chengzhi Lin, Chunhua Shen, Junwei Liang, Jun Zhang, Wei-Shi Zheng, Wenhang Ge","submitted_at":"2022-09-27T11:13:48Z","abstract_excerpt":"Cross-modal retrieval between videos and texts has gained increasing research interest due to the rapid emergence of videos on the web. Generally, a video contains rich instance and event information and the query text only describes a part of the information. Thus, a video can correspond to multiple different text descriptions and queries. We call this phenomenon the ``Video-Text Correspondence Ambiguity'' problem. Current techniques mostly concentrate on mining local or multi-level alignment between contents of a video and text (\\textit{e.g.}, object to entity and action to verb). It is diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13307","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/2209.13307/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":"2209.13307","created_at":"2026-07-05T05:01:09.159360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.13307v1","created_at":"2026-07-05T05:01:09.159360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13307","created_at":"2026-07-05T05:01:09.159360+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2BGN7ZPQPPO","created_at":"2026-07-05T05:01:09.159360+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2BGN7ZPQPPOBIHH","created_at":"2026-07-05T05:01:09.159360+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2BGN7ZP","created_at":"2026-07-05T05:01:09.159360+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/G2BGN7ZPQPPOBIHHR4ISAMLGZM","json":"https://pith.science/pith/G2BGN7ZPQPPOBIHHR4ISAMLGZM.json","graph_json":"https://pith.science/api/pith-number/G2BGN7ZPQPPOBIHHR4ISAMLGZM/graph.json","events_json":"https://pith.science/api/pith-number/G2BGN7ZPQPPOBIHHR4ISAMLGZM/events.json","paper":"https://pith.science/paper/G2BGN7ZP"},"agent_actions":{"view_html":"https://pith.science/pith/G2BGN7ZPQPPOBIHHR4ISAMLGZM","download_json":"https://pith.science/pith/G2BGN7ZPQPPOBIHHR4ISAMLGZM.json","view_paper":"https://pith.science/paper/G2BGN7ZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.13307&json=true","fetch_graph":"https://pith.science/api/pith-number/G2BGN7ZPQPPOBIHHR4ISAMLGZM/graph.json","fetch_events":"https://pith.science/api/pith-number/G2BGN7ZPQPPOBIHHR4ISAMLGZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2BGN7ZPQPPOBIHHR4ISAMLGZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2BGN7ZPQPPOBIHHR4ISAMLGZM/action/storage_attestation","attest_author":"https://pith.science/pith/G2BGN7ZPQPPOBIHHR4ISAMLGZM/action/author_attestation","sign_citation":"https://pith.science/pith/G2BGN7ZPQPPOBIHHR4ISAMLGZM/action/citation_signature","submit_replication":"https://pith.science/pith/G2BGN7ZPQPPOBIHHR4ISAMLGZM/action/replication_record"}},"created_at":"2026-07-05T05:01:09.159360+00:00","updated_at":"2026-07-05T05:01:09.159360+00:00"}