{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:S7EUAXEXZWNVP5DYFOZGCW6U75","short_pith_number":"pith:S7EUAXEX","schema_version":"1.0","canonical_sha256":"97c9405c97cd9b57f4782bb2615bd4ff4e910d554f03d225fbf9bd5f284fd146","source":{"kind":"arxiv","id":"1406.3332","version":2},"attestation_state":"computed","paper":{"title":"Convolutional Kernel Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid (INRIA Grenoble Rh\\^one-Alpes / LJK Laboratoire Jean Kuntzmann), Julien Mairal (INRIA Grenoble Rh\\^one-Alpes / LJK Laboratoire Jean Kuntzmann), Piotr Koniusz (INRIA Grenoble Rh\\^one-Alpes / LJK Laboratoire Jean Kuntzmann), Zaid Harchaoui (INRIA Grenoble Rh\\^one-Alpes / LJK Laboratoire Jean Kuntzmann)","submitted_at":"2014-06-12T19:41:03Z","abstract_excerpt":"An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is encoded by a reproducing kernel. Unlike traditional approaches where neural networks are learned either to represent data or for solving a classification task, our network learns to approximate the kernel feature map on training data. Such an approach enjoys several benefits over classical ones. First, by teaching CNNs to be invariant, we obtain simple network ar"},"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":"1406.3332","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-12T19:41:03Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"20e012c266d641276ae7c3fc034bd8a44edfb10cb45dad6175cc0a5c874afe32","abstract_canon_sha256":"d4e0599541d322c956d267326e1b5dc886f5998c6b4b37915ce332dd0216c6c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:30:01.050651Z","signature_b64":"roA1Bu2ViLe9gl4TL1spghpWK3k1DVKnUNPsGR0wuyaBBRf5WiHywdY5qLLzSatlx9OLFwHal8nhLS6lyIcgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97c9405c97cd9b57f4782bb2615bd4ff4e910d554f03d225fbf9bd5f284fd146","last_reissued_at":"2026-05-18T02:30:01.050174Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:30:01.050174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Kernel Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid (INRIA Grenoble Rh\\^one-Alpes / LJK Laboratoire Jean Kuntzmann), Julien Mairal (INRIA Grenoble Rh\\^one-Alpes / LJK Laboratoire Jean Kuntzmann), Piotr Koniusz (INRIA Grenoble Rh\\^one-Alpes / LJK Laboratoire Jean Kuntzmann), Zaid Harchaoui (INRIA Grenoble Rh\\^one-Alpes / LJK Laboratoire Jean Kuntzmann)","submitted_at":"2014-06-12T19:41:03Z","abstract_excerpt":"An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is encoded by a reproducing kernel. Unlike traditional approaches where neural networks are learned either to represent data or for solving a classification task, our network learns to approximate the kernel feature map on training data. Such an approach enjoys several benefits over classical ones. First, by teaching CNNs to be invariant, we obtain simple network ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.3332","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":"1406.3332","created_at":"2026-05-18T02:30:01.050258+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.3332v2","created_at":"2026-05-18T02:30:01.050258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.3332","created_at":"2026-05-18T02:30:01.050258+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7EUAXEXZWNV","created_at":"2026-05-18T12:28:49.207871+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7EUAXEXZWNVP5DY","created_at":"2026-05-18T12:28:49.207871+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7EUAXEX","created_at":"2026-05-18T12:28:49.207871+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/S7EUAXEXZWNVP5DYFOZGCW6U75","json":"https://pith.science/pith/S7EUAXEXZWNVP5DYFOZGCW6U75.json","graph_json":"https://pith.science/api/pith-number/S7EUAXEXZWNVP5DYFOZGCW6U75/graph.json","events_json":"https://pith.science/api/pith-number/S7EUAXEXZWNVP5DYFOZGCW6U75/events.json","paper":"https://pith.science/paper/S7EUAXEX"},"agent_actions":{"view_html":"https://pith.science/pith/S7EUAXEXZWNVP5DYFOZGCW6U75","download_json":"https://pith.science/pith/S7EUAXEXZWNVP5DYFOZGCW6U75.json","view_paper":"https://pith.science/paper/S7EUAXEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.3332&json=true","fetch_graph":"https://pith.science/api/pith-number/S7EUAXEXZWNVP5DYFOZGCW6U75/graph.json","fetch_events":"https://pith.science/api/pith-number/S7EUAXEXZWNVP5DYFOZGCW6U75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7EUAXEXZWNVP5DYFOZGCW6U75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7EUAXEXZWNVP5DYFOZGCW6U75/action/storage_attestation","attest_author":"https://pith.science/pith/S7EUAXEXZWNVP5DYFOZGCW6U75/action/author_attestation","sign_citation":"https://pith.science/pith/S7EUAXEXZWNVP5DYFOZGCW6U75/action/citation_signature","submit_replication":"https://pith.science/pith/S7EUAXEXZWNVP5DYFOZGCW6U75/action/replication_record"}},"created_at":"2026-05-18T02:30:01.050258+00:00","updated_at":"2026-05-18T02:30:01.050258+00:00"}