{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DPWCRILOGDMTS376FGTPOS3RIT","short_pith_number":"pith:DPWCRILO","schema_version":"1.0","canonical_sha256":"1bec28a16e30d9396ffe29a6f74b7144c3fb42ab97b58a4fa9915777b867c9d3","source":{"kind":"arxiv","id":"2103.11247","version":2},"attestation_state":"computed","paper":{"title":"Attention-Based Multimodal Image Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aviad Moreshet, Yosi Keller","submitted_at":"2021-03-20T21:14:24Z","abstract_excerpt":"We propose an attention-based approach for multimodal image patch matching using a Transformer encoder attending to the feature maps of a multiscale Siamese CNN. Our encoder is shown to efficiently aggregate multiscale image embeddings while emphasizing task-specific appearance-invariant image cues. We also introduce an attention-residual architecture, using a residual connection bypassing the encoder. This additional learning signal facilitates end-to-end training from scratch. Our approach is experimentally shown to achieve new state-of-the-art accuracy on both multimodal and single modality"},"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":"2103.11247","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-20T21:14:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"857999c77405ec1d00504c83b360d5d181f0525aa7ef3547cb67e48501d1d996","abstract_canon_sha256":"337dcba91b55d1e70caf8248506b1340eec920dc73732d49c216693a51cefdbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:28.039411Z","signature_b64":"OAiLcAGX30sd035O7BoDbwYsTCNzBstNbZOmjBycQIwFBgpKiaKcY3SzlD/ioSxQbQC2TWPI5GwAyDB+bgh5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bec28a16e30d9396ffe29a6f74b7144c3fb42ab97b58a4fa9915777b867c9d3","last_reissued_at":"2026-07-05T06:53:28.038969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:28.038969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention-Based Multimodal Image Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aviad Moreshet, Yosi Keller","submitted_at":"2021-03-20T21:14:24Z","abstract_excerpt":"We propose an attention-based approach for multimodal image patch matching using a Transformer encoder attending to the feature maps of a multiscale Siamese CNN. Our encoder is shown to efficiently aggregate multiscale image embeddings while emphasizing task-specific appearance-invariant image cues. We also introduce an attention-residual architecture, using a residual connection bypassing the encoder. This additional learning signal facilitates end-to-end training from scratch. Our approach is experimentally shown to achieve new state-of-the-art accuracy on both multimodal and single modality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11247","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.11247/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":"2103.11247","created_at":"2026-07-05T06:53:28.039023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.11247v2","created_at":"2026-07-05T06:53:28.039023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11247","created_at":"2026-07-05T06:53:28.039023+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPWCRILOGDMT","created_at":"2026-07-05T06:53:28.039023+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPWCRILOGDMTS376","created_at":"2026-07-05T06:53:28.039023+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPWCRILO","created_at":"2026-07-05T06:53:28.039023+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/DPWCRILOGDMTS376FGTPOS3RIT","json":"https://pith.science/pith/DPWCRILOGDMTS376FGTPOS3RIT.json","graph_json":"https://pith.science/api/pith-number/DPWCRILOGDMTS376FGTPOS3RIT/graph.json","events_json":"https://pith.science/api/pith-number/DPWCRILOGDMTS376FGTPOS3RIT/events.json","paper":"https://pith.science/paper/DPWCRILO"},"agent_actions":{"view_html":"https://pith.science/pith/DPWCRILOGDMTS376FGTPOS3RIT","download_json":"https://pith.science/pith/DPWCRILOGDMTS376FGTPOS3RIT.json","view_paper":"https://pith.science/paper/DPWCRILO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.11247&json=true","fetch_graph":"https://pith.science/api/pith-number/DPWCRILOGDMTS376FGTPOS3RIT/graph.json","fetch_events":"https://pith.science/api/pith-number/DPWCRILOGDMTS376FGTPOS3RIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPWCRILOGDMTS376FGTPOS3RIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPWCRILOGDMTS376FGTPOS3RIT/action/storage_attestation","attest_author":"https://pith.science/pith/DPWCRILOGDMTS376FGTPOS3RIT/action/author_attestation","sign_citation":"https://pith.science/pith/DPWCRILOGDMTS376FGTPOS3RIT/action/citation_signature","submit_replication":"https://pith.science/pith/DPWCRILOGDMTS376FGTPOS3RIT/action/replication_record"}},"created_at":"2026-07-05T06:53:28.039023+00:00","updated_at":"2026-07-05T06:53:28.039023+00:00"}