{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QIMSY2GMUWICJY6R6C44NQDVRD","short_pith_number":"pith:QIMSY2GM","schema_version":"1.0","canonical_sha256":"82192c68cca59024e3d1f0b9c6c07588c48909d9dedf57c95c7da1933d27ac45","source":{"kind":"arxiv","id":"2212.04979","version":3},"attestation_state":"computed","paper":{"title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jiahui Yu, Mi Zhang, Shen Yan, Soham Ghosh, Tao Zhu, Yonghui Wu, Yuan Cao, Zirui Wang","submitted_at":"2022-12-09T16:39:09Z","abstract_excerpt":"We explore an efficient approach to establish a foundational video-text model. We present VideoCoCa that maximally reuses a pretrained image-text contrastive captioner (CoCa) model and adapt it to video-text tasks with minimal extra training. While previous works adapt image-text models with various cross-frame fusion modules, we find that the generative attentional pooling and contrastive attentional pooling layers in CoCa are instantly adaptable to flattened frame embeddings, yielding state-of-the-art results on zero-shot video classification and zero-shot text-to-video retrieval. Furthermor"},"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":"2212.04979","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-09T16:39:09Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"fe5d36a7c2b6e63df19cb959d733c8f8d23be53150ba44b66ce7d00627ff055c","abstract_canon_sha256":"19a373415a3749ff947d263c56222448b19d9ff749f99de12e91157f4e64872d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:43.551240Z","signature_b64":"RdMgcELHo5nvDHugS76vX03IN0ldGZ54lImyt4B/nakDmYCmBkgXhRTLaYphwmpm91CITJ35cKtkEKqgznOiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82192c68cca59024e3d1f0b9c6c07588c48909d9dedf57c95c7da1933d27ac45","last_reissued_at":"2026-07-05T05:51:43.550750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:43.550750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jiahui Yu, Mi Zhang, Shen Yan, Soham Ghosh, Tao Zhu, Yonghui Wu, Yuan Cao, Zirui Wang","submitted_at":"2022-12-09T16:39:09Z","abstract_excerpt":"We explore an efficient approach to establish a foundational video-text model. We present VideoCoCa that maximally reuses a pretrained image-text contrastive captioner (CoCa) model and adapt it to video-text tasks with minimal extra training. While previous works adapt image-text models with various cross-frame fusion modules, we find that the generative attentional pooling and contrastive attentional pooling layers in CoCa are instantly adaptable to flattened frame embeddings, yielding state-of-the-art results on zero-shot video classification and zero-shot text-to-video retrieval. Furthermor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04979","kind":"arxiv","version":3},"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/2212.04979/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":"2212.04979","created_at":"2026-07-05T05:51:43.550812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04979v3","created_at":"2026-07-05T05:51:43.550812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04979","created_at":"2026-07-05T05:51:43.550812+00:00"},{"alias_kind":"pith_short_12","alias_value":"QIMSY2GMUWIC","created_at":"2026-07-05T05:51:43.550812+00:00"},{"alias_kind":"pith_short_16","alias_value":"QIMSY2GMUWICJY6R","created_at":"2026-07-05T05:51:43.550812+00:00"},{"alias_kind":"pith_short_8","alias_value":"QIMSY2GM","created_at":"2026-07-05T05:51:43.550812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.09176","citing_title":"LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02779","citing_title":"3D Foundation Model for Generalizable Disease Detection in Head Computed Tomography","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04590","citing_title":"VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01852","citing_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","ref_index":212,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QIMSY2GMUWICJY6R6C44NQDVRD","json":"https://pith.science/pith/QIMSY2GMUWICJY6R6C44NQDVRD.json","graph_json":"https://pith.science/api/pith-number/QIMSY2GMUWICJY6R6C44NQDVRD/graph.json","events_json":"https://pith.science/api/pith-number/QIMSY2GMUWICJY6R6C44NQDVRD/events.json","paper":"https://pith.science/paper/QIMSY2GM"},"agent_actions":{"view_html":"https://pith.science/pith/QIMSY2GMUWICJY6R6C44NQDVRD","download_json":"https://pith.science/pith/QIMSY2GMUWICJY6R6C44NQDVRD.json","view_paper":"https://pith.science/paper/QIMSY2GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04979&json=true","fetch_graph":"https://pith.science/api/pith-number/QIMSY2GMUWICJY6R6C44NQDVRD/graph.json","fetch_events":"https://pith.science/api/pith-number/QIMSY2GMUWICJY6R6C44NQDVRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QIMSY2GMUWICJY6R6C44NQDVRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QIMSY2GMUWICJY6R6C44NQDVRD/action/storage_attestation","attest_author":"https://pith.science/pith/QIMSY2GMUWICJY6R6C44NQDVRD/action/author_attestation","sign_citation":"https://pith.science/pith/QIMSY2GMUWICJY6R6C44NQDVRD/action/citation_signature","submit_replication":"https://pith.science/pith/QIMSY2GMUWICJY6R6C44NQDVRD/action/replication_record"}},"created_at":"2026-07-05T05:51:43.550812+00:00","updated_at":"2026-07-05T05:51:43.550812+00:00"}