{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3EOVQNCWUUI73YLUTHTM5FNOJI","short_pith_number":"pith:3EOVQNCW","schema_version":"1.0","canonical_sha256":"d91d583456a511fde17499e6ce95ae4a1a5bc129dc0d549bf1894eac87bbe18f","source":{"kind":"arxiv","id":"2211.13471","version":1},"attestation_state":"computed","paper":{"title":"Minority-Oriented Vicinity Expansion with Attentive Aggregation for Video Long-Tailed Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyun Seok Seong, Jae-Pil Heo, WonJun Moon","submitted_at":"2022-11-24T08:33:59Z","abstract_excerpt":"A dramatic increase in real-world video volume with extremely diverse and emerging topics naturally forms a long-tailed video distribution in terms of their categories, and it spotlights the need for Video Long-Tailed Recognition (VLTR). In this work, we summarize the challenges in VLTR and explore how to overcome them. The challenges are: (1) it is impractical to re-train the whole model for high-quality features, (2) acquiring frame-wise labels requires extensive cost, and (3) long-tailed data triggers biased training. Yet, most existing works for VLTR unavoidably utilize image-level feature"},"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":"2211.13471","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-24T08:33:59Z","cross_cats_sorted":[],"title_canon_sha256":"70ce84175531c77131620071038f820987a28557ce92fd3f2c7a6b23d6535f45","abstract_canon_sha256":"06ebfc060ef0bd7f88d919f2668cd4812e53ec81126e64a35b915417d7564f95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:22.649696Z","signature_b64":"w3XmoHooEKeIuCIXuRGAKHqpJLpSo1wqhb1mKsSUo0E+v80C1p5vA8igduYa1U6+Yxzdf6BtqV8XEOHD7Rg2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d91d583456a511fde17499e6ce95ae4a1a5bc129dc0d549bf1894eac87bbe18f","last_reissued_at":"2026-07-05T05:19:22.649203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:22.649203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minority-Oriented Vicinity Expansion with Attentive Aggregation for Video Long-Tailed Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyun Seok Seong, Jae-Pil Heo, WonJun Moon","submitted_at":"2022-11-24T08:33:59Z","abstract_excerpt":"A dramatic increase in real-world video volume with extremely diverse and emerging topics naturally forms a long-tailed video distribution in terms of their categories, and it spotlights the need for Video Long-Tailed Recognition (VLTR). In this work, we summarize the challenges in VLTR and explore how to overcome them. The challenges are: (1) it is impractical to re-train the whole model for high-quality features, (2) acquiring frame-wise labels requires extensive cost, and (3) long-tailed data triggers biased training. Yet, most existing works for VLTR unavoidably utilize image-level feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13471","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/2211.13471/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":"2211.13471","created_at":"2026-07-05T05:19:22.649256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13471v1","created_at":"2026-07-05T05:19:22.649256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13471","created_at":"2026-07-05T05:19:22.649256+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EOVQNCWUUI7","created_at":"2026-07-05T05:19:22.649256+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EOVQNCWUUI73YLU","created_at":"2026-07-05T05:19:22.649256+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EOVQNCW","created_at":"2026-07-05T05:19:22.649256+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/3EOVQNCWUUI73YLUTHTM5FNOJI","json":"https://pith.science/pith/3EOVQNCWUUI73YLUTHTM5FNOJI.json","graph_json":"https://pith.science/api/pith-number/3EOVQNCWUUI73YLUTHTM5FNOJI/graph.json","events_json":"https://pith.science/api/pith-number/3EOVQNCWUUI73YLUTHTM5FNOJI/events.json","paper":"https://pith.science/paper/3EOVQNCW"},"agent_actions":{"view_html":"https://pith.science/pith/3EOVQNCWUUI73YLUTHTM5FNOJI","download_json":"https://pith.science/pith/3EOVQNCWUUI73YLUTHTM5FNOJI.json","view_paper":"https://pith.science/paper/3EOVQNCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13471&json=true","fetch_graph":"https://pith.science/api/pith-number/3EOVQNCWUUI73YLUTHTM5FNOJI/graph.json","fetch_events":"https://pith.science/api/pith-number/3EOVQNCWUUI73YLUTHTM5FNOJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EOVQNCWUUI73YLUTHTM5FNOJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EOVQNCWUUI73YLUTHTM5FNOJI/action/storage_attestation","attest_author":"https://pith.science/pith/3EOVQNCWUUI73YLUTHTM5FNOJI/action/author_attestation","sign_citation":"https://pith.science/pith/3EOVQNCWUUI73YLUTHTM5FNOJI/action/citation_signature","submit_replication":"https://pith.science/pith/3EOVQNCWUUI73YLUTHTM5FNOJI/action/replication_record"}},"created_at":"2026-07-05T05:19:22.649256+00:00","updated_at":"2026-07-05T05:19:22.649256+00:00"}