{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XVNC5DECAYQPDJT3RGKQBIYUFJ","short_pith_number":"pith:XVNC5DEC","schema_version":"1.0","canonical_sha256":"bd5a2e8c820620f1a67b899500a3142a44d15a6844a22e283cb742dd02f285b3","source":{"kind":"arxiv","id":"2002.02651","version":1},"attestation_state":"computed","paper":{"title":"Learning Class Regularized Features for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Remco C. Veltkamp, Ronald Poppe","submitted_at":"2020-02-07T07:27:49Z","abstract_excerpt":"Training Deep Convolutional Neural Networks (CNNs) is based on the notion of using multiple kernels and non-linearities in their subsequent activations to extract useful features. The kernels are used as general feature extractors without specific correspondence to the target class. As a result, the extracted features do not correspond to specific classes. Subtle differences between similar classes are modeled in the same way as large differences between dissimilar classes. To overcome the class-agnostic use of kernels in CNNs, we introduce a novel method named Class Regularization that perfor"},"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":"2002.02651","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-07T07:27:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1e3f2e4b4253d88e50e0366080514197dfce75406145ce3cce68c0213ff681e2","abstract_canon_sha256":"004d3f01508beddc0bbcaf9a70b926cfa6f4ddf922245884c61647818caa0ce4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:05.977452Z","signature_b64":"lzr67EdSb4YQir0XugFwP4B1nCc+nCdE2dQ+N1q/3IkB3OO0CWd5FWXqjmqWxkevmmNhFsnbAFt8YssBDRk2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd5a2e8c820620f1a67b899500a3142a44d15a6844a22e283cb742dd02f285b3","last_reissued_at":"2026-07-05T01:51:05.976989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:05.976989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Class Regularized Features for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Remco C. Veltkamp, Ronald Poppe","submitted_at":"2020-02-07T07:27:49Z","abstract_excerpt":"Training Deep Convolutional Neural Networks (CNNs) is based on the notion of using multiple kernels and non-linearities in their subsequent activations to extract useful features. The kernels are used as general feature extractors without specific correspondence to the target class. As a result, the extracted features do not correspond to specific classes. Subtle differences between similar classes are modeled in the same way as large differences between dissimilar classes. To overcome the class-agnostic use of kernels in CNNs, we introduce a novel method named Class Regularization that perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02651","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/2002.02651/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":"2002.02651","created_at":"2026-07-05T01:51:05.977048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.02651v1","created_at":"2026-07-05T01:51:05.977048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02651","created_at":"2026-07-05T01:51:05.977048+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVNC5DECAYQP","created_at":"2026-07-05T01:51:05.977048+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVNC5DECAYQPDJT3","created_at":"2026-07-05T01:51:05.977048+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVNC5DEC","created_at":"2026-07-05T01:51:05.977048+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/XVNC5DECAYQPDJT3RGKQBIYUFJ","json":"https://pith.science/pith/XVNC5DECAYQPDJT3RGKQBIYUFJ.json","graph_json":"https://pith.science/api/pith-number/XVNC5DECAYQPDJT3RGKQBIYUFJ/graph.json","events_json":"https://pith.science/api/pith-number/XVNC5DECAYQPDJT3RGKQBIYUFJ/events.json","paper":"https://pith.science/paper/XVNC5DEC"},"agent_actions":{"view_html":"https://pith.science/pith/XVNC5DECAYQPDJT3RGKQBIYUFJ","download_json":"https://pith.science/pith/XVNC5DECAYQPDJT3RGKQBIYUFJ.json","view_paper":"https://pith.science/paper/XVNC5DEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.02651&json=true","fetch_graph":"https://pith.science/api/pith-number/XVNC5DECAYQPDJT3RGKQBIYUFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XVNC5DECAYQPDJT3RGKQBIYUFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVNC5DECAYQPDJT3RGKQBIYUFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVNC5DECAYQPDJT3RGKQBIYUFJ/action/storage_attestation","attest_author":"https://pith.science/pith/XVNC5DECAYQPDJT3RGKQBIYUFJ/action/author_attestation","sign_citation":"https://pith.science/pith/XVNC5DECAYQPDJT3RGKQBIYUFJ/action/citation_signature","submit_replication":"https://pith.science/pith/XVNC5DECAYQPDJT3RGKQBIYUFJ/action/replication_record"}},"created_at":"2026-07-05T01:51:05.977048+00:00","updated_at":"2026-07-05T01:51:05.977048+00:00"}