{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:XEGJHSB3QER4BEIBTU56QNL2K7","short_pith_number":"pith:XEGJHSB3","schema_version":"1.0","canonical_sha256":"b90c93c83b8123c091019d3be8357a57fcb77585478210c655270434541e7a2a","source":{"kind":"arxiv","id":"1608.04233","version":2},"attestation_state":"computed","paper":{"title":"A Riemannian Network for SPD Matrix Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Luc Van Gool, Zhiwu Huang","submitted_at":"2016-08-15T11:00:16Z","abstract_excerpt":"Symmetric Positive Definite (SPD) matrix learning methods have become popular in many image and video processing tasks, thanks to their ability to learn appropriate statistical representations while respecting Riemannian geometry of underlying SPD manifolds. In this paper we build a Riemannian network architecture to open up a new direction of SPD matrix non-linear learning in a deep model. In particular, we devise bilinear mapping layers to transform input SPD matrices to more desirable SPD matrices, exploit eigenvalue rectification layers to apply a non-linear activation function to the new "},"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":"1608.04233","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-15T11:00:16Z","cross_cats_sorted":[],"title_canon_sha256":"70a987204a4ff576c915945b9a8461cbb1cb78f9bcda9eac0f1f28bc072c82bf","abstract_canon_sha256":"20a06a7ffec9dcaff06cbe2dd63f6f4345367895f4466a36c2dd62d5a546a456"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:10.595943Z","signature_b64":"X4BhEGNzwZEC7NEioUcf3fgAE6LzTzOxVMaFnGJpioFjtqxvWLy2mcT+vyzRZ8tuWtduU0mU6+pvhhtai/nKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b90c93c83b8123c091019d3be8357a57fcb77585478210c655270434541e7a2a","last_reissued_at":"2026-05-18T00:54:10.595554Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:10.595554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Riemannian Network for SPD Matrix Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Luc Van Gool, Zhiwu Huang","submitted_at":"2016-08-15T11:00:16Z","abstract_excerpt":"Symmetric Positive Definite (SPD) matrix learning methods have become popular in many image and video processing tasks, thanks to their ability to learn appropriate statistical representations while respecting Riemannian geometry of underlying SPD manifolds. In this paper we build a Riemannian network architecture to open up a new direction of SPD matrix non-linear learning in a deep model. In particular, we devise bilinear mapping layers to transform input SPD matrices to more desirable SPD matrices, exploit eigenvalue rectification layers to apply a non-linear activation function to the new "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04233","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":""},"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":"1608.04233","created_at":"2026-05-18T00:54:10.595616+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.04233v2","created_at":"2026-05-18T00:54:10.595616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04233","created_at":"2026-05-18T00:54:10.595616+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEGJHSB3QER4","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEGJHSB3QER4BEIB","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEGJHSB3","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13648","citing_title":"Constitutive Manifold Neural Networks","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEGJHSB3QER4BEIBTU56QNL2K7","json":"https://pith.science/pith/XEGJHSB3QER4BEIBTU56QNL2K7.json","graph_json":"https://pith.science/api/pith-number/XEGJHSB3QER4BEIBTU56QNL2K7/graph.json","events_json":"https://pith.science/api/pith-number/XEGJHSB3QER4BEIBTU56QNL2K7/events.json","paper":"https://pith.science/paper/XEGJHSB3"},"agent_actions":{"view_html":"https://pith.science/pith/XEGJHSB3QER4BEIBTU56QNL2K7","download_json":"https://pith.science/pith/XEGJHSB3QER4BEIBTU56QNL2K7.json","view_paper":"https://pith.science/paper/XEGJHSB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.04233&json=true","fetch_graph":"https://pith.science/api/pith-number/XEGJHSB3QER4BEIBTU56QNL2K7/graph.json","fetch_events":"https://pith.science/api/pith-number/XEGJHSB3QER4BEIBTU56QNL2K7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEGJHSB3QER4BEIBTU56QNL2K7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEGJHSB3QER4BEIBTU56QNL2K7/action/storage_attestation","attest_author":"https://pith.science/pith/XEGJHSB3QER4BEIBTU56QNL2K7/action/author_attestation","sign_citation":"https://pith.science/pith/XEGJHSB3QER4BEIBTU56QNL2K7/action/citation_signature","submit_replication":"https://pith.science/pith/XEGJHSB3QER4BEIBTU56QNL2K7/action/replication_record"}},"created_at":"2026-05-18T00:54:10.595616+00:00","updated_at":"2026-05-18T00:54:10.595616+00:00"}