{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CZ4JEOB5APVPNWFUHGBIPSPZBQ","short_pith_number":"pith:CZ4JEOB5","schema_version":"1.0","canonical_sha256":"167892383d03eaf6d8b4398287c9f90c085fecd72cc7a7d78128acd9a5761f17","source":{"kind":"arxiv","id":"2211.00833","version":1},"attestation_state":"computed","paper":{"title":"Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Cen, Mingqian Tang, Nong Sang, Shiwei Zhang, Xiang Wang, Xueming Qian, Yaxiong Wang, Yixuan Pei, Zhiwu Qing","submitted_at":"2022-11-02T02:37:20Z","abstract_excerpt":"Recent incremental learning for action recognition usually stores representative videos to mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the limited memory. To address this problem, we propose FrameMaker, a memory-efficient video class-incremental learning approach that learns to produce a condensed frame for each selected video. Specifically, FrameMaker is mainly composed of two crucial components: Frame Condensing and Instance-Specific Prompt. The former is to reduce the memory cost by preserving only one condensed frame instead of the whole video, w"},"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":"2211.00833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-02T02:37:20Z","cross_cats_sorted":[],"title_canon_sha256":"17f7ff3b89c73a38dc7f63889672590fc9b2e562d6a1100d7444fb9bdf696601","abstract_canon_sha256":"50bcfb02ebc9fa22d6e2b3d86cb990dc273bd2ae7c59c4c09a0eff0beb0ef5db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:35.448492Z","signature_b64":"RFicAwMz+1+FkLM3KoggEYobwTB8UQw/sBywkMuwUHW+PBnll3magulvq+s59IIumubu2dylO9qPN/K5ZItDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167892383d03eaf6d8b4398287c9f90c085fecd72cc7a7d78128acd9a5761f17","last_reissued_at":"2026-07-05T05:12:35.448061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:35.448061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Cen, Mingqian Tang, Nong Sang, Shiwei Zhang, Xiang Wang, Xueming Qian, Yaxiong Wang, Yixuan Pei, Zhiwu Qing","submitted_at":"2022-11-02T02:37:20Z","abstract_excerpt":"Recent incremental learning for action recognition usually stores representative videos to mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the limited memory. To address this problem, we propose FrameMaker, a memory-efficient video class-incremental learning approach that learns to produce a condensed frame for each selected video. Specifically, FrameMaker is mainly composed of two crucial components: Frame Condensing and Instance-Specific Prompt. The former is to reduce the memory cost by preserving only one condensed frame instead of the whole video, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00833","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/2211.00833/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":"2211.00833","created_at":"2026-07-05T05:12:35.448127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00833v1","created_at":"2026-07-05T05:12:35.448127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00833","created_at":"2026-07-05T05:12:35.448127+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZ4JEOB5APVP","created_at":"2026-07-05T05:12:35.448127+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZ4JEOB5APVPNWFU","created_at":"2026-07-05T05:12:35.448127+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZ4JEOB5","created_at":"2026-07-05T05:12:35.448127+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/CZ4JEOB5APVPNWFUHGBIPSPZBQ","json":"https://pith.science/pith/CZ4JEOB5APVPNWFUHGBIPSPZBQ.json","graph_json":"https://pith.science/api/pith-number/CZ4JEOB5APVPNWFUHGBIPSPZBQ/graph.json","events_json":"https://pith.science/api/pith-number/CZ4JEOB5APVPNWFUHGBIPSPZBQ/events.json","paper":"https://pith.science/paper/CZ4JEOB5"},"agent_actions":{"view_html":"https://pith.science/pith/CZ4JEOB5APVPNWFUHGBIPSPZBQ","download_json":"https://pith.science/pith/CZ4JEOB5APVPNWFUHGBIPSPZBQ.json","view_paper":"https://pith.science/paper/CZ4JEOB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00833&json=true","fetch_graph":"https://pith.science/api/pith-number/CZ4JEOB5APVPNWFUHGBIPSPZBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CZ4JEOB5APVPNWFUHGBIPSPZBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZ4JEOB5APVPNWFUHGBIPSPZBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZ4JEOB5APVPNWFUHGBIPSPZBQ/action/storage_attestation","attest_author":"https://pith.science/pith/CZ4JEOB5APVPNWFUHGBIPSPZBQ/action/author_attestation","sign_citation":"https://pith.science/pith/CZ4JEOB5APVPNWFUHGBIPSPZBQ/action/citation_signature","submit_replication":"https://pith.science/pith/CZ4JEOB5APVPNWFUHGBIPSPZBQ/action/replication_record"}},"created_at":"2026-07-05T05:12:35.448127+00:00","updated_at":"2026-07-05T05:12:35.448127+00:00"}