{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZQNVGO4REU2VRS7CISZ72BTZMB","short_pith_number":"pith:ZQNVGO4R","schema_version":"1.0","canonical_sha256":"cc1b533b91253558cbe244b3fd0679605b4794e065d1fce37127b25de84f9179","source":{"kind":"arxiv","id":"2201.04850","version":2},"attestation_state":"computed","paper":{"title":"Bridging Video-text Retrieval with Multiple Choice Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dian Li, Ping Luo, Xiaohu Qie, Xihui Liu, Ying Shan, Yixiao Ge, Yuying Ge","submitted_at":"2022-01-13T09:33:54Z","abstract_excerpt":"Pre-training a model to learn transferable video-text representation for retrieval has attracted a lot of attention in recent years. Previous dominant works mainly adopt two separate encoders for efficient retrieval, but ignore local associations between videos and texts. Another line of research uses a joint encoder to interact video with texts, but results in low efficiency since each text-video pair needs to be fed into the model. In this work, we enable fine-grained video-text interactions while maintaining high efficiency for retrieval via a novel pretext task, dubbed as Multiple Choice Q"},"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":"2201.04850","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T09:33:54Z","cross_cats_sorted":[],"title_canon_sha256":"d370bc22c13dc733f38e8558b90ea723f2e47629288c9301855b6611b53227f6","abstract_canon_sha256":"4f414e43282130fdf8c2feb77ecb6bf79581d003365fdb0840f9ff88240c129e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:01.722384Z","signature_b64":"B9QvSrS/7WrV4GBw/pkG9KhkKrrLkJMFKq/TFBhzl8ub7G5tLwbfTFmLzOgHpvvZ9y9SVLO+3hCz8jtDKlVqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc1b533b91253558cbe244b3fd0679605b4794e065d1fce37127b25de84f9179","last_reissued_at":"2026-07-05T04:06:01.721875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:01.721875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Video-text Retrieval with Multiple Choice Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dian Li, Ping Luo, Xiaohu Qie, Xihui Liu, Ying Shan, Yixiao Ge, Yuying Ge","submitted_at":"2022-01-13T09:33:54Z","abstract_excerpt":"Pre-training a model to learn transferable video-text representation for retrieval has attracted a lot of attention in recent years. Previous dominant works mainly adopt two separate encoders for efficient retrieval, but ignore local associations between videos and texts. Another line of research uses a joint encoder to interact video with texts, but results in low efficiency since each text-video pair needs to be fed into the model. In this work, we enable fine-grained video-text interactions while maintaining high efficiency for retrieval via a novel pretext task, dubbed as Multiple Choice Q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04850","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/2201.04850/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":"2201.04850","created_at":"2026-07-05T04:06:01.721930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.04850v2","created_at":"2026-07-05T04:06:01.721930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04850","created_at":"2026-07-05T04:06:01.721930+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQNVGO4REU2V","created_at":"2026-07-05T04:06:01.721930+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQNVGO4REU2VRS7C","created_at":"2026-07-05T04:06:01.721930+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQNVGO4R","created_at":"2026-07-05T04:06:01.721930+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/ZQNVGO4REU2VRS7CISZ72BTZMB","json":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB.json","graph_json":"https://pith.science/api/pith-number/ZQNVGO4REU2VRS7CISZ72BTZMB/graph.json","events_json":"https://pith.science/api/pith-number/ZQNVGO4REU2VRS7CISZ72BTZMB/events.json","paper":"https://pith.science/paper/ZQNVGO4R"},"agent_actions":{"view_html":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB","download_json":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB.json","view_paper":"https://pith.science/paper/ZQNVGO4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.04850&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQNVGO4REU2VRS7CISZ72BTZMB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQNVGO4REU2VRS7CISZ72BTZMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB/action/storage_attestation","attest_author":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB/action/author_attestation","sign_citation":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB/action/citation_signature","submit_replication":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB/action/replication_record"}},"created_at":"2026-07-05T04:06:01.721930+00:00","updated_at":"2026-07-05T04:06:01.721930+00:00"}