{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RY5O5HB4IGYBC4WIRXP3PJJLT7","short_pith_number":"pith:RY5O5HB4","schema_version":"1.0","canonical_sha256":"8e3aee9c3c41b01172c88ddfb7a52b9fe78d293bf16bf7c6d83f9eb4be7c27eb","source":{"kind":"arxiv","id":"2104.00650","version":2},"attestation_state":"computed","paper":{"title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, G\\\"ul Varol, Max Bain","submitted_at":"2021-04-01T17:48:27Z","abstract_excerpt":"Our objective in this work is video-text retrieval - in particular a joint embedding that enables efficient text-to-video retrieval. The challenges in this area include the design of the visual architecture and the nature of the training data, in that the available large scale video-text training datasets, such as HowTo100M, are noisy and hence competitive performance is achieved only at scale through large amounts of compute. We address both these challenges in this paper. We propose an end-to-end trainable model that is designed to take advantage of both large-scale image and video captionin"},"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":"2104.00650","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T17:48:27Z","cross_cats_sorted":[],"title_canon_sha256":"56fda0e7c8fefb4de21e561f8a0eb0ce652ce29439d77ae3524a726c85ddbe30","abstract_canon_sha256":"7bf7d08dd1058559cd97fb88fe1eb15a61d965dd0467923f52ca2e78f1bf33f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:50.531095Z","signature_b64":"hETK898op98M9Hl58iG7c7Wo+SnJ21n0bUOdkcQ1vZx6/UQPmuNsN1eyz444WG1UWWx156Zxp3sjs/iYPzIVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e3aee9c3c41b01172c88ddfb7a52b9fe78d293bf16bf7c6d83f9eb4be7c27eb","last_reissued_at":"2026-07-05T04:22:50.530573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:50.530573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, G\\\"ul Varol, Max Bain","submitted_at":"2021-04-01T17:48:27Z","abstract_excerpt":"Our objective in this work is video-text retrieval - in particular a joint embedding that enables efficient text-to-video retrieval. The challenges in this area include the design of the visual architecture and the nature of the training data, in that the available large scale video-text training datasets, such as HowTo100M, are noisy and hence competitive performance is achieved only at scale through large amounts of compute. We address both these challenges in this paper. We propose an end-to-end trainable model that is designed to take advantage of both large-scale image and video captionin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00650","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/2104.00650/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":"2104.00650","created_at":"2026-07-05T04:22:50.530632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.00650v2","created_at":"2026-07-05T04:22:50.530632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00650","created_at":"2026-07-05T04:22:50.530632+00:00"},{"alias_kind":"pith_short_12","alias_value":"RY5O5HB4IGYB","created_at":"2026-07-05T04:22:50.530632+00:00"},{"alias_kind":"pith_short_16","alias_value":"RY5O5HB4IGYBC4WI","created_at":"2026-07-05T04:22:50.530632+00:00"},{"alias_kind":"pith_short_8","alias_value":"RY5O5HB4","created_at":"2026-07-05T04:22:50.530632+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05675","citing_title":"MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RY5O5HB4IGYBC4WIRXP3PJJLT7","json":"https://pith.science/pith/RY5O5HB4IGYBC4WIRXP3PJJLT7.json","graph_json":"https://pith.science/api/pith-number/RY5O5HB4IGYBC4WIRXP3PJJLT7/graph.json","events_json":"https://pith.science/api/pith-number/RY5O5HB4IGYBC4WIRXP3PJJLT7/events.json","paper":"https://pith.science/paper/RY5O5HB4"},"agent_actions":{"view_html":"https://pith.science/pith/RY5O5HB4IGYBC4WIRXP3PJJLT7","download_json":"https://pith.science/pith/RY5O5HB4IGYBC4WIRXP3PJJLT7.json","view_paper":"https://pith.science/paper/RY5O5HB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.00650&json=true","fetch_graph":"https://pith.science/api/pith-number/RY5O5HB4IGYBC4WIRXP3PJJLT7/graph.json","fetch_events":"https://pith.science/api/pith-number/RY5O5HB4IGYBC4WIRXP3PJJLT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RY5O5HB4IGYBC4WIRXP3PJJLT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RY5O5HB4IGYBC4WIRXP3PJJLT7/action/storage_attestation","attest_author":"https://pith.science/pith/RY5O5HB4IGYBC4WIRXP3PJJLT7/action/author_attestation","sign_citation":"https://pith.science/pith/RY5O5HB4IGYBC4WIRXP3PJJLT7/action/citation_signature","submit_replication":"https://pith.science/pith/RY5O5HB4IGYBC4WIRXP3PJJLT7/action/replication_record"}},"created_at":"2026-07-05T04:22:50.530632+00:00","updated_at":"2026-07-05T04:22:50.530632+00:00"}