{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7VYXUGQ7RWEZ4JE6DON4CYTYNR","short_pith_number":"pith:7VYXUGQ7","schema_version":"1.0","canonical_sha256":"fd717a1a1f8d899e249e1b9bc162786c44fa6a47ac69a5ff2ec27cb846873363","source":{"kind":"arxiv","id":"2407.10484","version":3},"attestation_state":"computed","paper":{"title":"Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gaowen Liu, Nicu Sebe, Xiao-Jun Wu, Yue Song, Ziheng Chen","submitted_at":"2024-07-15T07:11:44Z","abstract_excerpt":"Global Covariance Pooling (GCP) has been demonstrated to improve the performance of Deep Neural Networks (DNNs) by exploiting second-order statistics of high-level representations. GCP typically performs classification of the covariance matrices by applying matrix function normalization, such as matrix logarithm or power, followed by a Euclidean classifier. However, covariance matrices inherently lie in a Riemannian manifold, known as the Symmetric Positive Definite (SPD) manifold. The current literature does not provide a satisfactory explanation of why Euclidean classifiers can be applied di"},"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":"2407.10484","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T07:11:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"22426a552fe4878b14aef4b893f5f0412d8205adf0eb08c357fc986c4b064d3d","abstract_canon_sha256":"41a4d34310d00c324890d79e93e34c2d00afb6e1deb7733d75f0252fba83a4ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:22.102514Z","signature_b64":"3EUD5IRh0j0KOIF3ej25cTbWqbb3IL7rgGNZa89QgD8r2m+yfR7/NtXEvGCGP9ZWS28TUZ1QOAy9HIMgKjLYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd717a1a1f8d899e249e1b9bc162786c44fa6a47ac69a5ff2ec27cb846873363","last_reissued_at":"2026-07-05T10:11:22.101833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:22.101833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gaowen Liu, Nicu Sebe, Xiao-Jun Wu, Yue Song, Ziheng Chen","submitted_at":"2024-07-15T07:11:44Z","abstract_excerpt":"Global Covariance Pooling (GCP) has been demonstrated to improve the performance of Deep Neural Networks (DNNs) by exploiting second-order statistics of high-level representations. GCP typically performs classification of the covariance matrices by applying matrix function normalization, such as matrix logarithm or power, followed by a Euclidean classifier. However, covariance matrices inherently lie in a Riemannian manifold, known as the Symmetric Positive Definite (SPD) manifold. The current literature does not provide a satisfactory explanation of why Euclidean classifiers can be applied di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10484","kind":"arxiv","version":3},"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/2407.10484/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":"2407.10484","created_at":"2026-07-05T10:11:22.101931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10484v3","created_at":"2026-07-05T10:11:22.101931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10484","created_at":"2026-07-05T10:11:22.101931+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VYXUGQ7RWEZ","created_at":"2026-07-05T10:11:22.101931+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VYXUGQ7RWEZ4JE6","created_at":"2026-07-05T10:11:22.101931+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VYXUGQ7","created_at":"2026-07-05T10:11:22.101931+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/7VYXUGQ7RWEZ4JE6DON4CYTYNR","json":"https://pith.science/pith/7VYXUGQ7RWEZ4JE6DON4CYTYNR.json","graph_json":"https://pith.science/api/pith-number/7VYXUGQ7RWEZ4JE6DON4CYTYNR/graph.json","events_json":"https://pith.science/api/pith-number/7VYXUGQ7RWEZ4JE6DON4CYTYNR/events.json","paper":"https://pith.science/paper/7VYXUGQ7"},"agent_actions":{"view_html":"https://pith.science/pith/7VYXUGQ7RWEZ4JE6DON4CYTYNR","download_json":"https://pith.science/pith/7VYXUGQ7RWEZ4JE6DON4CYTYNR.json","view_paper":"https://pith.science/paper/7VYXUGQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10484&json=true","fetch_graph":"https://pith.science/api/pith-number/7VYXUGQ7RWEZ4JE6DON4CYTYNR/graph.json","fetch_events":"https://pith.science/api/pith-number/7VYXUGQ7RWEZ4JE6DON4CYTYNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VYXUGQ7RWEZ4JE6DON4CYTYNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VYXUGQ7RWEZ4JE6DON4CYTYNR/action/storage_attestation","attest_author":"https://pith.science/pith/7VYXUGQ7RWEZ4JE6DON4CYTYNR/action/author_attestation","sign_citation":"https://pith.science/pith/7VYXUGQ7RWEZ4JE6DON4CYTYNR/action/citation_signature","submit_replication":"https://pith.science/pith/7VYXUGQ7RWEZ4JE6DON4CYTYNR/action/replication_record"}},"created_at":"2026-07-05T10:11:22.101931+00:00","updated_at":"2026-07-05T10:11:22.101931+00:00"}