{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6NW2NTB4QD3JXUTQHBCJOQURSI","short_pith_number":"pith:6NW2NTB4","schema_version":"1.0","canonical_sha256":"f36da6cc3c80f69bd27038449742919209c16b18c149bcd1f6be6ba86fbcb488","source":{"kind":"arxiv","id":"1806.09183","version":1},"attestation_state":"computed","paper":{"title":"A Deeper Look at Power Normalizations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Hongguang Zhang, Piotr Koniusz","submitted_at":"2018-06-24T17:38:15Z","abstract_excerpt":"Power Normalizations (PN) are very useful non-linear operators in the context of Bag-of-Words data representations as they tackle problems such as feature imbalance. In this paper, we reconsider these operators in the deep learning setup by introducing a novel layer that implements PN for non-linear pooling of feature maps. Specifically, by using a kernel formulation, our layer combines the feature vectors and their respective spatial locations in the feature maps produced by the last convolutional layer of CNN. Linearization of such a kernel results in a positive definite matrix capturing the"},"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":"1806.09183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-24T17:38:15Z","cross_cats_sorted":[],"title_canon_sha256":"1115ca9fccce4ba888069064f85b764d3e9d5062bf9968ba8f9d9e8a96755561","abstract_canon_sha256":"e8480f6e11414f33b99317764dbe1fe696aa79649166456258501bc957059178"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:30.070452Z","signature_b64":"E43+9O80kEhKDL06eikRyKD0gC16BCn71vy3wdvKAFbXMT6eUkXWwkwxrl/f9U5qCUNbbu2vCjbUpp4Lxa1WAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f36da6cc3c80f69bd27038449742919209c16b18c149bcd1f6be6ba86fbcb488","last_reissued_at":"2026-05-18T00:12:30.069965Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:30.069965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Deeper Look at Power Normalizations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Hongguang Zhang, Piotr Koniusz","submitted_at":"2018-06-24T17:38:15Z","abstract_excerpt":"Power Normalizations (PN) are very useful non-linear operators in the context of Bag-of-Words data representations as they tackle problems such as feature imbalance. In this paper, we reconsider these operators in the deep learning setup by introducing a novel layer that implements PN for non-linear pooling of feature maps. Specifically, by using a kernel formulation, our layer combines the feature vectors and their respective spatial locations in the feature maps produced by the last convolutional layer of CNN. Linearization of such a kernel results in a positive definite matrix capturing the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09183","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":"1806.09183","created_at":"2026-05-18T00:12:30.070039+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.09183v1","created_at":"2026-05-18T00:12:30.070039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09183","created_at":"2026-05-18T00:12:30.070039+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NW2NTB4QD3J","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NW2NTB4QD3JXUTQ","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NW2NTB4","created_at":"2026-05-18T12:32:11.075285+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/6NW2NTB4QD3JXUTQHBCJOQURSI","json":"https://pith.science/pith/6NW2NTB4QD3JXUTQHBCJOQURSI.json","graph_json":"https://pith.science/api/pith-number/6NW2NTB4QD3JXUTQHBCJOQURSI/graph.json","events_json":"https://pith.science/api/pith-number/6NW2NTB4QD3JXUTQHBCJOQURSI/events.json","paper":"https://pith.science/paper/6NW2NTB4"},"agent_actions":{"view_html":"https://pith.science/pith/6NW2NTB4QD3JXUTQHBCJOQURSI","download_json":"https://pith.science/pith/6NW2NTB4QD3JXUTQHBCJOQURSI.json","view_paper":"https://pith.science/paper/6NW2NTB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.09183&json=true","fetch_graph":"https://pith.science/api/pith-number/6NW2NTB4QD3JXUTQHBCJOQURSI/graph.json","fetch_events":"https://pith.science/api/pith-number/6NW2NTB4QD3JXUTQHBCJOQURSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NW2NTB4QD3JXUTQHBCJOQURSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NW2NTB4QD3JXUTQHBCJOQURSI/action/storage_attestation","attest_author":"https://pith.science/pith/6NW2NTB4QD3JXUTQHBCJOQURSI/action/author_attestation","sign_citation":"https://pith.science/pith/6NW2NTB4QD3JXUTQHBCJOQURSI/action/citation_signature","submit_replication":"https://pith.science/pith/6NW2NTB4QD3JXUTQHBCJOQURSI/action/replication_record"}},"created_at":"2026-05-18T00:12:30.070039+00:00","updated_at":"2026-05-18T00:12:30.070039+00:00"}