{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UJYODH7GO2MNBLRWJXGO7TPEVI","short_pith_number":"pith:UJYODH7G","schema_version":"1.0","canonical_sha256":"a270e19fe67698d0ae364dccefcde4aa0ef3d39d59553579c4c4a6927f06fc74","source":{"kind":"arxiv","id":"2109.14910","version":1},"attestation_state":"computed","paper":{"title":"CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Mohammadreza Zolfaghari, Peter Gehler, Thomas Brox, Yi Zhu","submitted_at":"2021-09-30T08:12:21Z","abstract_excerpt":"Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without exploiting its full potential. In particular, previous losses do not take the intra-modality similarities into account, which leads to inefficient embeddings, as the same content is mapped to multiple points in the embedding space. With CrossCLR, we present a contrastive loss that fixes this issue. Moreover, we define sets of highly related samples in terms of the"},"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":"2109.14910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-30T08:12:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a01f8d0a15c873310e19dcfcf0dfed477df399eca4b2e9c8266d5cccfb695cb1","abstract_canon_sha256":"f430f7f792156ce2c4f0c3dbef35525ca4b3c8f1257fd9026cdce62f8ebfa623"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:45.558288Z","signature_b64":"qDIkcRc9UNY0/myVyvSMNYGi2QdAFGMGigal6Kwa5d7UEDU9lUPrl/mvcSscJhdiJ6NsZ0Z7DAehABpQgYNBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a270e19fe67698d0ae364dccefcde4aa0ef3d39d59553579c4c4a6927f06fc74","last_reissued_at":"2026-07-05T03:18:45.557952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:45.557952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Mohammadreza Zolfaghari, Peter Gehler, Thomas Brox, Yi Zhu","submitted_at":"2021-09-30T08:12:21Z","abstract_excerpt":"Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without exploiting its full potential. In particular, previous losses do not take the intra-modality similarities into account, which leads to inefficient embeddings, as the same content is mapped to multiple points in the embedding space. With CrossCLR, we present a contrastive loss that fixes this issue. Moreover, we define sets of highly related samples in terms of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.14910","kind":"arxiv","version":1},"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/2109.14910/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":"2109.14910","created_at":"2026-07-05T03:18:45.558009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.14910v1","created_at":"2026-07-05T03:18:45.558009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.14910","created_at":"2026-07-05T03:18:45.558009+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJYODH7GO2MN","created_at":"2026-07-05T03:18:45.558009+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJYODH7GO2MNBLRW","created_at":"2026-07-05T03:18:45.558009+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJYODH7G","created_at":"2026-07-05T03:18:45.558009+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/UJYODH7GO2MNBLRWJXGO7TPEVI","json":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI.json","graph_json":"https://pith.science/api/pith-number/UJYODH7GO2MNBLRWJXGO7TPEVI/graph.json","events_json":"https://pith.science/api/pith-number/UJYODH7GO2MNBLRWJXGO7TPEVI/events.json","paper":"https://pith.science/paper/UJYODH7G"},"agent_actions":{"view_html":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI","download_json":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI.json","view_paper":"https://pith.science/paper/UJYODH7G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.14910&json=true","fetch_graph":"https://pith.science/api/pith-number/UJYODH7GO2MNBLRWJXGO7TPEVI/graph.json","fetch_events":"https://pith.science/api/pith-number/UJYODH7GO2MNBLRWJXGO7TPEVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI/action/storage_attestation","attest_author":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI/action/author_attestation","sign_citation":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI/action/citation_signature","submit_replication":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI/action/replication_record"}},"created_at":"2026-07-05T03:18:45.558009+00:00","updated_at":"2026-07-05T03:18:45.558009+00:00"}