{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HFLKYV7XDKV66QSXJRCNQAHTV7","short_pith_number":"pith:HFLKYV7X","schema_version":"1.0","canonical_sha256":"3956ac57f71aabef42574c44d800f3afc0fd396fdfd7e14bd7e0acc39be6dcd1","source":{"kind":"arxiv","id":"1703.06817","version":1},"attestation_state":"computed","paper":{"title":"Second-order Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaicheng Yu, Mathieu Salzmann","submitted_at":"2017-03-20T16:05:21Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) have been successfully applied to many computer vision tasks, such as image classification. By performing linear combinations and element-wise nonlinear operations, these networks can be thought of as extracting solely first-order information from an input image. In the past, however, second-order statistics computed from handcrafted features, e.g., covariances, have proven highly effective in diverse recognition tasks. In this paper, we introduce a novel class of CNNs that exploit second-order statistics. To this end, we design a series of new layers that "},"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":"1703.06817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-20T16:05:21Z","cross_cats_sorted":[],"title_canon_sha256":"ea3e284c5f115c01136a2ac21e1f84688b1541374d452624e6c2dddf7218caa5","abstract_canon_sha256":"26c29a681fa55e186ea04846e3eed2fb4ad9153dc7b956bcf60aa0359ed140b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:21.637559Z","signature_b64":"lzPGQ5yN9378JPt7CrtNsRfvFiFHlNSRfkeZrGdCm5oxYMvhhwweNGcrrrjtuEmUQ4myHY71ayPAfJHX6c14Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3956ac57f71aabef42574c44d800f3afc0fd396fdfd7e14bd7e0acc39be6dcd1","last_reissued_at":"2026-05-18T00:48:21.636912Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:21.636912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Second-order Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaicheng Yu, Mathieu Salzmann","submitted_at":"2017-03-20T16:05:21Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) have been successfully applied to many computer vision tasks, such as image classification. By performing linear combinations and element-wise nonlinear operations, these networks can be thought of as extracting solely first-order information from an input image. In the past, however, second-order statistics computed from handcrafted features, e.g., covariances, have proven highly effective in diverse recognition tasks. In this paper, we introduce a novel class of CNNs that exploit second-order statistics. To this end, we design a series of new layers that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06817","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":""},"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":"1703.06817","created_at":"2026-05-18T00:48:21.637002+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.06817v1","created_at":"2026-05-18T00:48:21.637002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06817","created_at":"2026-05-18T00:48:21.637002+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFLKYV7XDKV6","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFLKYV7XDKV66QSX","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFLKYV7X","created_at":"2026-05-18T12:31:18.294218+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/HFLKYV7XDKV66QSXJRCNQAHTV7","json":"https://pith.science/pith/HFLKYV7XDKV66QSXJRCNQAHTV7.json","graph_json":"https://pith.science/api/pith-number/HFLKYV7XDKV66QSXJRCNQAHTV7/graph.json","events_json":"https://pith.science/api/pith-number/HFLKYV7XDKV66QSXJRCNQAHTV7/events.json","paper":"https://pith.science/paper/HFLKYV7X"},"agent_actions":{"view_html":"https://pith.science/pith/HFLKYV7XDKV66QSXJRCNQAHTV7","download_json":"https://pith.science/pith/HFLKYV7XDKV66QSXJRCNQAHTV7.json","view_paper":"https://pith.science/paper/HFLKYV7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.06817&json=true","fetch_graph":"https://pith.science/api/pith-number/HFLKYV7XDKV66QSXJRCNQAHTV7/graph.json","fetch_events":"https://pith.science/api/pith-number/HFLKYV7XDKV66QSXJRCNQAHTV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFLKYV7XDKV66QSXJRCNQAHTV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFLKYV7XDKV66QSXJRCNQAHTV7/action/storage_attestation","attest_author":"https://pith.science/pith/HFLKYV7XDKV66QSXJRCNQAHTV7/action/author_attestation","sign_citation":"https://pith.science/pith/HFLKYV7XDKV66QSXJRCNQAHTV7/action/citation_signature","submit_replication":"https://pith.science/pith/HFLKYV7XDKV66QSXJRCNQAHTV7/action/replication_record"}},"created_at":"2026-05-18T00:48:21.637002+00:00","updated_at":"2026-05-18T00:48:21.637002+00:00"}