{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YDFPPCZ4B57H2CTFU7ZQMOLX6O","short_pith_number":"pith:YDFPPCZ4","schema_version":"1.0","canonical_sha256":"c0caf78b3c0f7e7d0a65a7f3063977f38b7d1d5ee55534a7fbeaa4002553a4ea","source":{"kind":"arxiv","id":"1905.12871","version":1},"attestation_state":"computed","paper":{"title":"A Trainable Multiplication Layer for Auto-correlation and Co-occurrence Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hideaki Hayashi, Seiichi Uchida","submitted_at":"2019-05-30T06:21:54Z","abstract_excerpt":"In this paper, we propose a trainable multiplication layer (TML) for a neural network that can be used to calculate the multiplication between the input features. Taking an image as an input, the TML raises each pixel value to the power of a weight and then multiplies them, thereby extracting the higher-order local auto-correlation from the input image. The TML can also be used to extract co-occurrence from the feature map of a convolutional network. The training of the TML is formulated based on backpropagation with constraints to the weights, enabling us to learn discriminative multiplicatio"},"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":"1905.12871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T06:21:54Z","cross_cats_sorted":[],"title_canon_sha256":"f7e6b1f74560a206e601953afad6cf35ecf006ac58eef4fa5dca908bd60981bb","abstract_canon_sha256":"e4d4af48f5ed0a4f1a443a217e48dd5927df2b308012212651e992b2fe97dddb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:39.438595Z","signature_b64":"px5d+VmPBaZvq9lowFTiRLxStltXqEeSvZTcb4cNvBHwnby8nRkf84i3YeJ6KEj43KkkeRkjJmgxN1XvmE4CDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0caf78b3c0f7e7d0a65a7f3063977f38b7d1d5ee55534a7fbeaa4002553a4ea","last_reissued_at":"2026-05-17T23:44:39.438042Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:39.438042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Trainable Multiplication Layer for Auto-correlation and Co-occurrence Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hideaki Hayashi, Seiichi Uchida","submitted_at":"2019-05-30T06:21:54Z","abstract_excerpt":"In this paper, we propose a trainable multiplication layer (TML) for a neural network that can be used to calculate the multiplication between the input features. Taking an image as an input, the TML raises each pixel value to the power of a weight and then multiplies them, thereby extracting the higher-order local auto-correlation from the input image. The TML can also be used to extract co-occurrence from the feature map of a convolutional network. The training of the TML is formulated based on backpropagation with constraints to the weights, enabling us to learn discriminative multiplicatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12871","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":"1905.12871","created_at":"2026-05-17T23:44:39.438115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12871v1","created_at":"2026-05-17T23:44:39.438115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12871","created_at":"2026-05-17T23:44:39.438115+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDFPPCZ4B57H","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDFPPCZ4B57H2CTF","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDFPPCZ4","created_at":"2026-05-18T12:33:33.725879+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/YDFPPCZ4B57H2CTFU7ZQMOLX6O","json":"https://pith.science/pith/YDFPPCZ4B57H2CTFU7ZQMOLX6O.json","graph_json":"https://pith.science/api/pith-number/YDFPPCZ4B57H2CTFU7ZQMOLX6O/graph.json","events_json":"https://pith.science/api/pith-number/YDFPPCZ4B57H2CTFU7ZQMOLX6O/events.json","paper":"https://pith.science/paper/YDFPPCZ4"},"agent_actions":{"view_html":"https://pith.science/pith/YDFPPCZ4B57H2CTFU7ZQMOLX6O","download_json":"https://pith.science/pith/YDFPPCZ4B57H2CTFU7ZQMOLX6O.json","view_paper":"https://pith.science/paper/YDFPPCZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12871&json=true","fetch_graph":"https://pith.science/api/pith-number/YDFPPCZ4B57H2CTFU7ZQMOLX6O/graph.json","fetch_events":"https://pith.science/api/pith-number/YDFPPCZ4B57H2CTFU7ZQMOLX6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDFPPCZ4B57H2CTFU7ZQMOLX6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDFPPCZ4B57H2CTFU7ZQMOLX6O/action/storage_attestation","attest_author":"https://pith.science/pith/YDFPPCZ4B57H2CTFU7ZQMOLX6O/action/author_attestation","sign_citation":"https://pith.science/pith/YDFPPCZ4B57H2CTFU7ZQMOLX6O/action/citation_signature","submit_replication":"https://pith.science/pith/YDFPPCZ4B57H2CTFU7ZQMOLX6O/action/replication_record"}},"created_at":"2026-05-17T23:44:39.438115+00:00","updated_at":"2026-05-17T23:44:39.438115+00:00"}