{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:36YI5M5WQRC4GKZA7PICDTYUCM","short_pith_number":"pith:36YI5M5W","schema_version":"1.0","canonical_sha256":"dfb08eb3b68445c32b20fbd021cf141322b345bf98cbeec5cdaa34524a3c2f37","source":{"kind":"arxiv","id":"2008.02711","version":1},"attestation_state":"computed","paper":{"title":"Exploring Relations in Untrimmed Videos for Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Fang, Dayan Wu, Dezhao Luo, Weiping Wang, Yucan Zhou, Yu Zhou","submitted_at":"2020-08-06T15:29:25Z","abstract_excerpt":"Existing video self-supervised learning methods mainly rely on trimmed videos for model training. However, trimmed datasets are manually annotated from untrimmed videos. In this sense, these methods are not really self-supervised. In this paper, we propose a novel self-supervised method, referred to as Exploring Relations in Untrimmed Videos (ERUV), which can be straightforwardly applied to untrimmed videos (real unlabeled) to learn spatio-temporal features. ERUV first generates single-shot videos by shot change detection. Then a designed sampling strategy is used to model relations for video "},"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":"2008.02711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-06T15:29:25Z","cross_cats_sorted":[],"title_canon_sha256":"815fc8df9f823d1bb6c7874c79a7c6446fea4cad37e6ca5156806e6db6f24149","abstract_canon_sha256":"241fedff7915d1db67315360cf5ce2cc5e159d94d0221c06f1550bc5ff642858"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:18.810606Z","signature_b64":"MktD/DbxMMC+UVgSSV87EWzbGHeWGYcZuttPuPWTSSHsOHl8av/cneeQjVtBU/eAUJS3PSJ56nHsemLaDWwSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfb08eb3b68445c32b20fbd021cf141322b345bf98cbeec5cdaa34524a3c2f37","last_reissued_at":"2026-07-05T01:25:18.810251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:18.810251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Relations in Untrimmed Videos for Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Fang, Dayan Wu, Dezhao Luo, Weiping Wang, Yucan Zhou, Yu Zhou","submitted_at":"2020-08-06T15:29:25Z","abstract_excerpt":"Existing video self-supervised learning methods mainly rely on trimmed videos for model training. However, trimmed datasets are manually annotated from untrimmed videos. In this sense, these methods are not really self-supervised. In this paper, we propose a novel self-supervised method, referred to as Exploring Relations in Untrimmed Videos (ERUV), which can be straightforwardly applied to untrimmed videos (real unlabeled) to learn spatio-temporal features. ERUV first generates single-shot videos by shot change detection. Then a designed sampling strategy is used to model relations for video "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02711","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/2008.02711/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":"2008.02711","created_at":"2026-07-05T01:25:18.810302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.02711v1","created_at":"2026-07-05T01:25:18.810302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02711","created_at":"2026-07-05T01:25:18.810302+00:00"},{"alias_kind":"pith_short_12","alias_value":"36YI5M5WQRC4","created_at":"2026-07-05T01:25:18.810302+00:00"},{"alias_kind":"pith_short_16","alias_value":"36YI5M5WQRC4GKZA","created_at":"2026-07-05T01:25:18.810302+00:00"},{"alias_kind":"pith_short_8","alias_value":"36YI5M5W","created_at":"2026-07-05T01:25:18.810302+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/36YI5M5WQRC4GKZA7PICDTYUCM","json":"https://pith.science/pith/36YI5M5WQRC4GKZA7PICDTYUCM.json","graph_json":"https://pith.science/api/pith-number/36YI5M5WQRC4GKZA7PICDTYUCM/graph.json","events_json":"https://pith.science/api/pith-number/36YI5M5WQRC4GKZA7PICDTYUCM/events.json","paper":"https://pith.science/paper/36YI5M5W"},"agent_actions":{"view_html":"https://pith.science/pith/36YI5M5WQRC4GKZA7PICDTYUCM","download_json":"https://pith.science/pith/36YI5M5WQRC4GKZA7PICDTYUCM.json","view_paper":"https://pith.science/paper/36YI5M5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.02711&json=true","fetch_graph":"https://pith.science/api/pith-number/36YI5M5WQRC4GKZA7PICDTYUCM/graph.json","fetch_events":"https://pith.science/api/pith-number/36YI5M5WQRC4GKZA7PICDTYUCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36YI5M5WQRC4GKZA7PICDTYUCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36YI5M5WQRC4GKZA7PICDTYUCM/action/storage_attestation","attest_author":"https://pith.science/pith/36YI5M5WQRC4GKZA7PICDTYUCM/action/author_attestation","sign_citation":"https://pith.science/pith/36YI5M5WQRC4GKZA7PICDTYUCM/action/citation_signature","submit_replication":"https://pith.science/pith/36YI5M5WQRC4GKZA7PICDTYUCM/action/replication_record"}},"created_at":"2026-07-05T01:25:18.810302+00:00","updated_at":"2026-07-05T01:25:18.810302+00:00"}