{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XFKFT6SJMKZQPFX4A63ZSDYZRQ","short_pith_number":"pith:XFKFT6SJ","schema_version":"1.0","canonical_sha256":"b95459fa4962b30796fc07b7990f198c251ecc3116a4c828bc8547e6f32d2e44","source":{"kind":"arxiv","id":"1908.01259","version":3},"attestation_state":"computed","paper":{"title":"Attentive Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tianfu Wu, Wei Sun, Xilai Li","submitted_at":"2019-08-04T02:17:34Z","abstract_excerpt":"In state-of-the-art deep neural networks, both feature normalization and feature attention have become ubiquitous. % with significant performance improvement shown in a vast amount of tasks. They are usually studied as separate modules, however. In this paper, we propose a light-weight integration between the two schema and present Attentive Normalization (AN). Instead of learning a single affine transformation, AN learns a mixture of affine transformations and utilizes their weighted-sum as the final affine transformation applied to re-calibrate features in an instance-specific way. The weigh"},"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":"1908.01259","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-04T02:17:34Z","cross_cats_sorted":[],"title_canon_sha256":"c6037c966b453984865520e60522301911614d67a0f27f8410739074ed36679e","abstract_canon_sha256":"b307745a47c38459d10b9f032ca0bdfded265367351557c8a12a6ab393186003"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:10.398049Z","signature_b64":"rXQxosTotdWXuvoMGmKUcmOMRmLOoo+ptsPZVaFb2gFJ/KlmUsAiVOqYgWFEY72g9B/gbPxZqqoTStLxnQApDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b95459fa4962b30796fc07b7990f198c251ecc3116a4c828bc8547e6f32d2e44","last_reissued_at":"2026-07-05T02:26:10.397705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:10.397705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attentive Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tianfu Wu, Wei Sun, Xilai Li","submitted_at":"2019-08-04T02:17:34Z","abstract_excerpt":"In state-of-the-art deep neural networks, both feature normalization and feature attention have become ubiquitous. % with significant performance improvement shown in a vast amount of tasks. They are usually studied as separate modules, however. In this paper, we propose a light-weight integration between the two schema and present Attentive Normalization (AN). Instead of learning a single affine transformation, AN learns a mixture of affine transformations and utilizes their weighted-sum as the final affine transformation applied to re-calibrate features in an instance-specific way. The weigh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01259","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/1908.01259/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":"1908.01259","created_at":"2026-07-05T02:26:10.397759+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.01259v3","created_at":"2026-07-05T02:26:10.397759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01259","created_at":"2026-07-05T02:26:10.397759+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFKFT6SJMKZQ","created_at":"2026-07-05T02:26:10.397759+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFKFT6SJMKZQPFX4","created_at":"2026-07-05T02:26:10.397759+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFKFT6SJ","created_at":"2026-07-05T02:26:10.397759+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/XFKFT6SJMKZQPFX4A63ZSDYZRQ","json":"https://pith.science/pith/XFKFT6SJMKZQPFX4A63ZSDYZRQ.json","graph_json":"https://pith.science/api/pith-number/XFKFT6SJMKZQPFX4A63ZSDYZRQ/graph.json","events_json":"https://pith.science/api/pith-number/XFKFT6SJMKZQPFX4A63ZSDYZRQ/events.json","paper":"https://pith.science/paper/XFKFT6SJ"},"agent_actions":{"view_html":"https://pith.science/pith/XFKFT6SJMKZQPFX4A63ZSDYZRQ","download_json":"https://pith.science/pith/XFKFT6SJMKZQPFX4A63ZSDYZRQ.json","view_paper":"https://pith.science/paper/XFKFT6SJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.01259&json=true","fetch_graph":"https://pith.science/api/pith-number/XFKFT6SJMKZQPFX4A63ZSDYZRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XFKFT6SJMKZQPFX4A63ZSDYZRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFKFT6SJMKZQPFX4A63ZSDYZRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFKFT6SJMKZQPFX4A63ZSDYZRQ/action/storage_attestation","attest_author":"https://pith.science/pith/XFKFT6SJMKZQPFX4A63ZSDYZRQ/action/author_attestation","sign_citation":"https://pith.science/pith/XFKFT6SJMKZQPFX4A63ZSDYZRQ/action/citation_signature","submit_replication":"https://pith.science/pith/XFKFT6SJMKZQPFX4A63ZSDYZRQ/action/replication_record"}},"created_at":"2026-07-05T02:26:10.397759+00:00","updated_at":"2026-07-05T02:26:10.397759+00:00"}