{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ENBNCE26Z2YYDEVKSLKL2REWL3","short_pith_number":"pith:ENBNCE26","schema_version":"1.0","canonical_sha256":"2342d1135eceb18192aa92d4bd44965ef9369448d748c7430b3dba583e78e190","source":{"kind":"arxiv","id":"2103.10211","version":2},"attestation_state":"computed","paper":{"title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Bernie Huang, Florian Metze, Ishan Misra, Joao Henriques, Mandela Patrick, Yuki M. Asano","submitted_at":"2021-03-18T12:32:24Z","abstract_excerpt":"The quality of the image representations obtained from self-supervised learning depends strongly on the type of data augmentations used in the learning formulation. Recent papers have ported these methods from still images to videos and found that leveraging both audio and video signals yields strong gains; however, they did not find that spatial augmentations such as cropping, which are very important for still images, work as well for videos. In this paper, we improve these formulations in two ways unique to the spatio-temporal aspect of videos. First, for space, we show that spatial augment"},"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":"2103.10211","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-18T12:32:24Z","cross_cats_sorted":[],"title_canon_sha256":"b623619e8872637e5637e408f7da76d333a9cbe8d68be3f2dd52cc7de6b5e723","abstract_canon_sha256":"7da215c3eb9fa5ee1cb7fa76a8d7408e131d2b459e7b0d600cb61a99493f137d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:15.889569Z","signature_b64":"cpvBdULBdbU1Bt96CilN01R0CaaIwqruVl8QmbFy/nfjNq5jHLh6hvxgNzQOcUS7hrAAH+iezuZcLkPQs7YKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2342d1135eceb18192aa92d4bd44965ef9369448d748c7430b3dba583e78e190","last_reissued_at":"2026-07-05T03:26:15.889037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:15.889037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Bernie Huang, Florian Metze, Ishan Misra, Joao Henriques, Mandela Patrick, Yuki M. Asano","submitted_at":"2021-03-18T12:32:24Z","abstract_excerpt":"The quality of the image representations obtained from self-supervised learning depends strongly on the type of data augmentations used in the learning formulation. Recent papers have ported these methods from still images to videos and found that leveraging both audio and video signals yields strong gains; however, they did not find that spatial augmentations such as cropping, which are very important for still images, work as well for videos. In this paper, we improve these formulations in two ways unique to the spatio-temporal aspect of videos. First, for space, we show that spatial augment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10211","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/2103.10211/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":"2103.10211","created_at":"2026-07-05T03:26:15.889093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.10211v2","created_at":"2026-07-05T03:26:15.889093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10211","created_at":"2026-07-05T03:26:15.889093+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENBNCE26Z2YY","created_at":"2026-07-05T03:26:15.889093+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENBNCE26Z2YYDEVK","created_at":"2026-07-05T03:26:15.889093+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENBNCE26","created_at":"2026-07-05T03:26:15.889093+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/ENBNCE26Z2YYDEVKSLKL2REWL3","json":"https://pith.science/pith/ENBNCE26Z2YYDEVKSLKL2REWL3.json","graph_json":"https://pith.science/api/pith-number/ENBNCE26Z2YYDEVKSLKL2REWL3/graph.json","events_json":"https://pith.science/api/pith-number/ENBNCE26Z2YYDEVKSLKL2REWL3/events.json","paper":"https://pith.science/paper/ENBNCE26"},"agent_actions":{"view_html":"https://pith.science/pith/ENBNCE26Z2YYDEVKSLKL2REWL3","download_json":"https://pith.science/pith/ENBNCE26Z2YYDEVKSLKL2REWL3.json","view_paper":"https://pith.science/paper/ENBNCE26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.10211&json=true","fetch_graph":"https://pith.science/api/pith-number/ENBNCE26Z2YYDEVKSLKL2REWL3/graph.json","fetch_events":"https://pith.science/api/pith-number/ENBNCE26Z2YYDEVKSLKL2REWL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENBNCE26Z2YYDEVKSLKL2REWL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENBNCE26Z2YYDEVKSLKL2REWL3/action/storage_attestation","attest_author":"https://pith.science/pith/ENBNCE26Z2YYDEVKSLKL2REWL3/action/author_attestation","sign_citation":"https://pith.science/pith/ENBNCE26Z2YYDEVKSLKL2REWL3/action/citation_signature","submit_replication":"https://pith.science/pith/ENBNCE26Z2YYDEVKSLKL2REWL3/action/replication_record"}},"created_at":"2026-07-05T03:26:15.889093+00:00","updated_at":"2026-07-05T03:26:15.889093+00:00"}