{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:U7ANNP5S6GQDPAZIVG4KKIAHEH","short_pith_number":"pith:U7ANNP5S","schema_version":"1.0","canonical_sha256":"a7c0d6bfb2f1a0378328a9b8a5200721e02097f25ae7f230a6625d981a6d8499","source":{"kind":"arxiv","id":"2206.04790","version":2},"attestation_state":"computed","paper":{"title":"Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Frank Keller, Laura Sevilla-Lara, Marcus Rohrbach, Shreyank N Gowda","submitted_at":"2022-06-09T23:04:52Z","abstract_excerpt":"We address the problem of data augmentation for video action recognition. Standard augmentation strategies in video are hand-designed and sample the space of possible augmented data points either at random, without knowing which augmented points will be better, or through heuristics. We propose to learn what makes a good video for action recognition and select only high-quality samples for augmentation. In particular, we choose video compositing of a foreground and a background video as the data augmentation process, which results in diverse and realistic new samples. We learn which pairs of v"},"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":"2206.04790","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-09T23:04:52Z","cross_cats_sorted":[],"title_canon_sha256":"d40c154e0a461bc6473fd68ba285abd9d913248045b32dd353e1354fa0060fea","abstract_canon_sha256":"ee3dd1198ca39c5e61e7a441bb83be463427cf5e2dfad0976076fd74ee93f0bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:02.566203Z","signature_b64":"3gKRJSyF85lDaNSfyE7813f+iaQUDb4drjt2wywt1RUZTnf9ZCRwr7WVKpvuiB/g3npSI60SVsukMVX3mn3zBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7c0d6bfb2f1a0378328a9b8a5200721e02097f25ae7f230a6625d981a6d8499","last_reissued_at":"2026-07-05T04:43:02.565761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:02.565761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Frank Keller, Laura Sevilla-Lara, Marcus Rohrbach, Shreyank N Gowda","submitted_at":"2022-06-09T23:04:52Z","abstract_excerpt":"We address the problem of data augmentation for video action recognition. Standard augmentation strategies in video are hand-designed and sample the space of possible augmented data points either at random, without knowing which augmented points will be better, or through heuristics. We propose to learn what makes a good video for action recognition and select only high-quality samples for augmentation. In particular, we choose video compositing of a foreground and a background video as the data augmentation process, which results in diverse and realistic new samples. We learn which pairs of v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04790","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/2206.04790/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":"2206.04790","created_at":"2026-07-05T04:43:02.565815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04790v2","created_at":"2026-07-05T04:43:02.565815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04790","created_at":"2026-07-05T04:43:02.565815+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7ANNP5S6GQD","created_at":"2026-07-05T04:43:02.565815+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7ANNP5S6GQDPAZI","created_at":"2026-07-05T04:43:02.565815+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7ANNP5S","created_at":"2026-07-05T04:43:02.565815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09411","citing_title":"Synthetic Human Action Video Data Generation with Pose Transfer","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7ANNP5S6GQDPAZIVG4KKIAHEH","json":"https://pith.science/pith/U7ANNP5S6GQDPAZIVG4KKIAHEH.json","graph_json":"https://pith.science/api/pith-number/U7ANNP5S6GQDPAZIVG4KKIAHEH/graph.json","events_json":"https://pith.science/api/pith-number/U7ANNP5S6GQDPAZIVG4KKIAHEH/events.json","paper":"https://pith.science/paper/U7ANNP5S"},"agent_actions":{"view_html":"https://pith.science/pith/U7ANNP5S6GQDPAZIVG4KKIAHEH","download_json":"https://pith.science/pith/U7ANNP5S6GQDPAZIVG4KKIAHEH.json","view_paper":"https://pith.science/paper/U7ANNP5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04790&json=true","fetch_graph":"https://pith.science/api/pith-number/U7ANNP5S6GQDPAZIVG4KKIAHEH/graph.json","fetch_events":"https://pith.science/api/pith-number/U7ANNP5S6GQDPAZIVG4KKIAHEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7ANNP5S6GQDPAZIVG4KKIAHEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7ANNP5S6GQDPAZIVG4KKIAHEH/action/storage_attestation","attest_author":"https://pith.science/pith/U7ANNP5S6GQDPAZIVG4KKIAHEH/action/author_attestation","sign_citation":"https://pith.science/pith/U7ANNP5S6GQDPAZIVG4KKIAHEH/action/citation_signature","submit_replication":"https://pith.science/pith/U7ANNP5S6GQDPAZIVG4KKIAHEH/action/replication_record"}},"created_at":"2026-07-05T04:43:02.565815+00:00","updated_at":"2026-07-05T04:43:02.565815+00:00"}