{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:R3RRXSB3W6QRGOAKJMSV6UTIPZ","short_pith_number":"pith:R3RRXSB3","schema_version":"1.0","canonical_sha256":"8ee31bc83bb7a113380a4b255f52687e571f78696f521c2e8ec4ba9ce961bc6a","source":{"kind":"arxiv","id":"2112.04478","version":2},"attestation_state":"computed","paper":{"title":"Prompting Visual-Language Models for Efficient Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chen Ju, Kunhao Zheng, Tengda Han, Weidi Xie, Ya Zhang","submitted_at":"2021-12-08T18:58:16Z","abstract_excerpt":"Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation. This paper presents a simple but strong baseline to efficiently adapt the pre-trained I-VL model, and exploit its powerful ability for resource-hungry video understanding tasks, with minimal training. Specifically, we propose to optimise a few random vectors, termed as continuous prompt vectors, that convert video-related tasks into the same format as the pre-training objectives. In additi"},"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":"2112.04478","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T18:58:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5f0bd99a51f5aca953cea495a520eb1b68d2f3c68fa61ec5b3051205b645df94","abstract_canon_sha256":"b58d1d5be7ef5a04e179e1aaae34bda480c551bf3b21ce170a3813bfacf68605"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:24.786558Z","signature_b64":"N1pyFR/G9rfloXt5oSRMgErMu8VcJzdwTeMchpd0zb2VBPNwvHBsX8S90UciXwIfbfs052hq2WJIDp4RNIFgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ee31bc83bb7a113380a4b255f52687e571f78696f521c2e8ec4ba9ce961bc6a","last_reissued_at":"2026-07-05T04:40:24.786036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:24.786036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompting Visual-Language Models for Efficient Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chen Ju, Kunhao Zheng, Tengda Han, Weidi Xie, Ya Zhang","submitted_at":"2021-12-08T18:58:16Z","abstract_excerpt":"Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation. This paper presents a simple but strong baseline to efficiently adapt the pre-trained I-VL model, and exploit its powerful ability for resource-hungry video understanding tasks, with minimal training. Specifically, we propose to optimise a few random vectors, termed as continuous prompt vectors, that convert video-related tasks into the same format as the pre-training objectives. In additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04478","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/2112.04478/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":"2112.04478","created_at":"2026-07-05T04:40:24.786100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.04478v2","created_at":"2026-07-05T04:40:24.786100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04478","created_at":"2026-07-05T04:40:24.786100+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3RRXSB3W6QR","created_at":"2026-07-05T04:40:24.786100+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3RRXSB3W6QRGOAK","created_at":"2026-07-05T04:40:24.786100+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3RRXSB3","created_at":"2026-07-05T04:40:24.786100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2407.17491","citing_title":"Robust Adaptation of Foundation Models with Black-Box Visual Prompting","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3RRXSB3W6QRGOAKJMSV6UTIPZ","json":"https://pith.science/pith/R3RRXSB3W6QRGOAKJMSV6UTIPZ.json","graph_json":"https://pith.science/api/pith-number/R3RRXSB3W6QRGOAKJMSV6UTIPZ/graph.json","events_json":"https://pith.science/api/pith-number/R3RRXSB3W6QRGOAKJMSV6UTIPZ/events.json","paper":"https://pith.science/paper/R3RRXSB3"},"agent_actions":{"view_html":"https://pith.science/pith/R3RRXSB3W6QRGOAKJMSV6UTIPZ","download_json":"https://pith.science/pith/R3RRXSB3W6QRGOAKJMSV6UTIPZ.json","view_paper":"https://pith.science/paper/R3RRXSB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.04478&json=true","fetch_graph":"https://pith.science/api/pith-number/R3RRXSB3W6QRGOAKJMSV6UTIPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/R3RRXSB3W6QRGOAKJMSV6UTIPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3RRXSB3W6QRGOAKJMSV6UTIPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3RRXSB3W6QRGOAKJMSV6UTIPZ/action/storage_attestation","attest_author":"https://pith.science/pith/R3RRXSB3W6QRGOAKJMSV6UTIPZ/action/author_attestation","sign_citation":"https://pith.science/pith/R3RRXSB3W6QRGOAKJMSV6UTIPZ/action/citation_signature","submit_replication":"https://pith.science/pith/R3RRXSB3W6QRGOAKJMSV6UTIPZ/action/replication_record"}},"created_at":"2026-07-05T04:40:24.786100+00:00","updated_at":"2026-07-05T04:40:24.786100+00:00"}