{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6PCIGWKKL25H4TUYWFVZRLFPSH","short_pith_number":"pith:6PCIGWKK","schema_version":"1.0","canonical_sha256":"f3c483594a5eba7e4e98b16b98acaf91ff5552d0f1fc1120a3ba31655f4823e4","source":{"kind":"arxiv","id":"2107.01194","version":3},"attestation_state":"computed","paper":{"title":"Inter-intra Variant Dual Representations forSelf-supervised Video Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changhu Wang, Lin Zhang, Qi She, Zhengyang Shen","submitted_at":"2021-07-02T17:03:04Z","abstract_excerpt":"Contrastive learning applied to self-supervised representation learning has seen a resurgence in deep models. In this paper, we find that existing contrastive learning based solutions for self-supervised video recognition focus on inter-variance encoding but ignore the intra-variance existing in clips within the same video. We thus propose to learn dual representations for each clip which (\\romannumeral 1) encode intra-variance through a shuffle-rank pretext task; (\\romannumeral 2) encode inter-variance through a temporal coherent contrastive loss. Experiment results show that our method plays"},"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":"2107.01194","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-02T17:03:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c74cd82289c6b34e0bde6e345739fd9156477142419a7d0349bfe39d55eba427","abstract_canon_sha256":"c974dc4679e6fab1c5c5dceb198a6ecf4ab25fdd49091a91dcb89eef389071dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:57.899344Z","signature_b64":"NuwO0aqJv/FQ6RQNMoXSOsJLSdDd+bGvYuaPfIG4PN1pFi75OPWb/UegUK26wvoh+tHVlU8AgL12EbgkaMFtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3c483594a5eba7e4e98b16b98acaf91ff5552d0f1fc1120a3ba31655f4823e4","last_reissued_at":"2026-07-05T03:24:57.898893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:57.898893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inter-intra Variant Dual Representations forSelf-supervised Video Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changhu Wang, Lin Zhang, Qi She, Zhengyang Shen","submitted_at":"2021-07-02T17:03:04Z","abstract_excerpt":"Contrastive learning applied to self-supervised representation learning has seen a resurgence in deep models. In this paper, we find that existing contrastive learning based solutions for self-supervised video recognition focus on inter-variance encoding but ignore the intra-variance existing in clips within the same video. We thus propose to learn dual representations for each clip which (\\romannumeral 1) encode intra-variance through a shuffle-rank pretext task; (\\romannumeral 2) encode inter-variance through a temporal coherent contrastive loss. Experiment results show that our method plays"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01194","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/2107.01194/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":"2107.01194","created_at":"2026-07-05T03:24:57.898943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.01194v3","created_at":"2026-07-05T03:24:57.898943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01194","created_at":"2026-07-05T03:24:57.898943+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PCIGWKKL25H","created_at":"2026-07-05T03:24:57.898943+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PCIGWKKL25H4TUY","created_at":"2026-07-05T03:24:57.898943+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PCIGWKK","created_at":"2026-07-05T03:24:57.898943+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/6PCIGWKKL25H4TUYWFVZRLFPSH","json":"https://pith.science/pith/6PCIGWKKL25H4TUYWFVZRLFPSH.json","graph_json":"https://pith.science/api/pith-number/6PCIGWKKL25H4TUYWFVZRLFPSH/graph.json","events_json":"https://pith.science/api/pith-number/6PCIGWKKL25H4TUYWFVZRLFPSH/events.json","paper":"https://pith.science/paper/6PCIGWKK"},"agent_actions":{"view_html":"https://pith.science/pith/6PCIGWKKL25H4TUYWFVZRLFPSH","download_json":"https://pith.science/pith/6PCIGWKKL25H4TUYWFVZRLFPSH.json","view_paper":"https://pith.science/paper/6PCIGWKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.01194&json=true","fetch_graph":"https://pith.science/api/pith-number/6PCIGWKKL25H4TUYWFVZRLFPSH/graph.json","fetch_events":"https://pith.science/api/pith-number/6PCIGWKKL25H4TUYWFVZRLFPSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PCIGWKKL25H4TUYWFVZRLFPSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PCIGWKKL25H4TUYWFVZRLFPSH/action/storage_attestation","attest_author":"https://pith.science/pith/6PCIGWKKL25H4TUYWFVZRLFPSH/action/author_attestation","sign_citation":"https://pith.science/pith/6PCIGWKKL25H4TUYWFVZRLFPSH/action/citation_signature","submit_replication":"https://pith.science/pith/6PCIGWKKL25H4TUYWFVZRLFPSH/action/replication_record"}},"created_at":"2026-07-05T03:24:57.898943+00:00","updated_at":"2026-07-05T03:24:57.898943+00:00"}