{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DPWCRILOGDMTS376FGTPOS3RIT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"337dcba91b55d1e70caf8248506b1340eec920dc73732d49c216693a51cefdbe","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-20T21:14:24Z","title_canon_sha256":"857999c77405ec1d00504c83b360d5d181f0525aa7ef3547cb67e48501d1d996"},"schema_version":"1.0","source":{"id":"2103.11247","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.11247","created_at":"2026-07-05T06:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2103.11247v2","created_at":"2026-07-05T06:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11247","created_at":"2026-07-05T06:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"DPWCRILOGDMT","created_at":"2026-07-05T06:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"DPWCRILOGDMTS376","created_at":"2026-07-05T06:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"DPWCRILO","created_at":"2026-07-05T06:53:28Z"}],"graph_snapshots":[{"event_id":"sha256:3d58b3c88d51b5eb8c20466d52225027f4a29f5fe7747721cac4e4238a0f4008","target":"graph","created_at":"2026-07-05T06:53:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.11247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aviad Moreshet, Yosi Keller","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-20T21:14:24Z","title":"Attention-Based Multimodal Image Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11247","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2bceb43008287710b4f898490e91dde54a10457166b8331680fc289cd5cc5674","target":"record","created_at":"2026-07-05T06:53:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"337dcba91b55d1e70caf8248506b1340eec920dc73732d49c216693a51cefdbe","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-20T21:14:24Z","title_canon_sha256":"857999c77405ec1d00504c83b360d5d181f0525aa7ef3547cb67e48501d1d996"},"schema_version":"1.0","source":{"id":"2103.11247","kind":"arxiv","version":2}},"canonical_sha256":"1bec28a16e30d9396ffe29a6f74b7144c3fb42ab97b58a4fa9915777b867c9d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bec28a16e30d9396ffe29a6f74b7144c3fb42ab97b58a4fa9915777b867c9d3","first_computed_at":"2026-07-05T06:53:28.038969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:28.038969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OAiLcAGX30sd035O7BoDbwYsTCNzBstNbZOmjBycQIwFBgpKiaKcY3SzlD/ioSxQbQC2TWPI5GwAyDB+bgh5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:28.039411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.11247","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bceb43008287710b4f898490e91dde54a10457166b8331680fc289cd5cc5674","sha256:3d58b3c88d51b5eb8c20466d52225027f4a29f5fe7747721cac4e4238a0f4008"],"state_sha256":"f55e15faf72a2496f59891d929bd75934a9392c49a331422e568de31546e03ca"}