{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:62MDTFSVKPKBC3TSD4MGFQA5LA","short_pith_number":"pith:62MDTFSV","schema_version":"1.0","canonical_sha256":"f69839965553d4116e721f1862c01d583bea208c1f2454a90491a428930bf129","source":{"kind":"arxiv","id":"2304.10335","version":2},"attestation_state":"computed","paper":{"title":"A baseline on continual learning methods for video action recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Concetto Spampinato, Daniela Giordano, Francesco Rundo, Giulia Castagnolo, Simone Palazzo","submitted_at":"2023-04-20T14:20:43Z","abstract_excerpt":"Continual learning has recently attracted attention from the research community, as it aims to solve long-standing limitations of classic supervisedly-trained models. However, most research on this subject has tackled continual learning in simple image classification scenarios. In this paper, we present a benchmark of state-of-the-art continual learning methods on video action recognition. Besides the increased complexity due to the temporal dimension, the video setting imposes stronger requirements on computing resources for top-performing rehearsal methods. To counteract the increased memory"},"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":"2304.10335","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T14:20:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"29344b859fb454761915ef0c1844fdc44e665b253e948c60c4e7f94fad6e0940","abstract_canon_sha256":"86f971ce44325f220ef0361314dc72752e05211c2836f78aac7d4900cdbecad1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:38.341727Z","signature_b64":"kZUODOeTkyduLspO8/l8qOVZm/6VGt82n6h29a+/6nds+SuYeThWwV9rbBhtAyfKGLen6m6AYSsnBdDx/VMfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f69839965553d4116e721f1862c01d583bea208c1f2454a90491a428930bf129","last_reissued_at":"2026-07-05T06:04:38.341281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:38.341281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A baseline on continual learning methods for video action recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Concetto Spampinato, Daniela Giordano, Francesco Rundo, Giulia Castagnolo, Simone Palazzo","submitted_at":"2023-04-20T14:20:43Z","abstract_excerpt":"Continual learning has recently attracted attention from the research community, as it aims to solve long-standing limitations of classic supervisedly-trained models. However, most research on this subject has tackled continual learning in simple image classification scenarios. In this paper, we present a benchmark of state-of-the-art continual learning methods on video action recognition. Besides the increased complexity due to the temporal dimension, the video setting imposes stronger requirements on computing resources for top-performing rehearsal methods. To counteract the increased memory"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10335","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/2304.10335/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":"2304.10335","created_at":"2026-07-05T06:04:38.341336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10335v2","created_at":"2026-07-05T06:04:38.341336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10335","created_at":"2026-07-05T06:04:38.341336+00:00"},{"alias_kind":"pith_short_12","alias_value":"62MDTFSVKPKB","created_at":"2026-07-05T06:04:38.341336+00:00"},{"alias_kind":"pith_short_16","alias_value":"62MDTFSVKPKBC3TS","created_at":"2026-07-05T06:04:38.341336+00:00"},{"alias_kind":"pith_short_8","alias_value":"62MDTFSV","created_at":"2026-07-05T06:04:38.341336+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/62MDTFSVKPKBC3TSD4MGFQA5LA","json":"https://pith.science/pith/62MDTFSVKPKBC3TSD4MGFQA5LA.json","graph_json":"https://pith.science/api/pith-number/62MDTFSVKPKBC3TSD4MGFQA5LA/graph.json","events_json":"https://pith.science/api/pith-number/62MDTFSVKPKBC3TSD4MGFQA5LA/events.json","paper":"https://pith.science/paper/62MDTFSV"},"agent_actions":{"view_html":"https://pith.science/pith/62MDTFSVKPKBC3TSD4MGFQA5LA","download_json":"https://pith.science/pith/62MDTFSVKPKBC3TSD4MGFQA5LA.json","view_paper":"https://pith.science/paper/62MDTFSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10335&json=true","fetch_graph":"https://pith.science/api/pith-number/62MDTFSVKPKBC3TSD4MGFQA5LA/graph.json","fetch_events":"https://pith.science/api/pith-number/62MDTFSVKPKBC3TSD4MGFQA5LA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62MDTFSVKPKBC3TSD4MGFQA5LA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62MDTFSVKPKBC3TSD4MGFQA5LA/action/storage_attestation","attest_author":"https://pith.science/pith/62MDTFSVKPKBC3TSD4MGFQA5LA/action/author_attestation","sign_citation":"https://pith.science/pith/62MDTFSVKPKBC3TSD4MGFQA5LA/action/citation_signature","submit_replication":"https://pith.science/pith/62MDTFSVKPKBC3TSD4MGFQA5LA/action/replication_record"}},"created_at":"2026-07-05T06:04:38.341336+00:00","updated_at":"2026-07-05T06:04:38.341336+00:00"}