{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:O5QVQ7PEJ755I4BNPKKQISLMB4","short_pith_number":"pith:O5QVQ7PE","schema_version":"1.0","canonical_sha256":"7761587de44ffbd4702d7a9504496c0f0831b5df820052f9b7f0d2fba265b0dc","source":{"kind":"arxiv","id":"2202.06817","version":2},"attestation_state":"computed","paper":{"title":"CATs++: Boosting Cost Aggregation with Convolutions and Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Seokju Cho, Seungryong Kim, Sunghwan Hong","submitted_at":"2022-02-14T15:54:58Z","abstract_excerpt":"Cost aggregation is a highly important process in image matching tasks, which aims to disambiguate the noisy matching scores. Existing methods generally tackle this by hand-crafted or CNN-based methods, which either lack robustness to severe deformations or inherit the limitation of CNNs that fail to discriminate incorrect matches due to limited receptive fields and inadaptability. In this paper, we introduce Cost Aggregation with Transformers (CATs) to tackle this by exploring global consensus among initial correlation map with the help of some architectural designs that allow us to fully enj"},"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":"2202.06817","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-14T15:54:58Z","cross_cats_sorted":[],"title_canon_sha256":"40fe480c9196fc5fbc7d4da8477b0f0394a73367f001fea8dac914c4bbdef679","abstract_canon_sha256":"2ad24c95dac7ab566ad431361d9d73285930d879d95fa620a7076a29d6fd44ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:37.083347Z","signature_b64":"hjKboQK4YdspXNjKZkZsjNARKG1xUkIeIdw9fT0+TexSH+GefgP21e0lsq6aix3QIcb4FPftUTqV92sMS9c7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7761587de44ffbd4702d7a9504496c0f0831b5df820052f9b7f0d2fba265b0dc","last_reissued_at":"2026-07-05T05:11:37.082738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:37.082738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CATs++: Boosting Cost Aggregation with Convolutions and Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Seokju Cho, Seungryong Kim, Sunghwan Hong","submitted_at":"2022-02-14T15:54:58Z","abstract_excerpt":"Cost aggregation is a highly important process in image matching tasks, which aims to disambiguate the noisy matching scores. Existing methods generally tackle this by hand-crafted or CNN-based methods, which either lack robustness to severe deformations or inherit the limitation of CNNs that fail to discriminate incorrect matches due to limited receptive fields and inadaptability. In this paper, we introduce Cost Aggregation with Transformers (CATs) to tackle this by exploring global consensus among initial correlation map with the help of some architectural designs that allow us to fully enj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06817","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/2202.06817/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":"2202.06817","created_at":"2026-07-05T05:11:37.082813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.06817v2","created_at":"2026-07-05T05:11:37.082813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06817","created_at":"2026-07-05T05:11:37.082813+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5QVQ7PEJ755","created_at":"2026-07-05T05:11:37.082813+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5QVQ7PEJ755I4BN","created_at":"2026-07-05T05:11:37.082813+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5QVQ7PE","created_at":"2026-07-05T05:11:37.082813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00272","citing_title":"Towards Robust Semantic Correspondence: A Benchmark and Insights","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O5QVQ7PEJ755I4BNPKKQISLMB4","json":"https://pith.science/pith/O5QVQ7PEJ755I4BNPKKQISLMB4.json","graph_json":"https://pith.science/api/pith-number/O5QVQ7PEJ755I4BNPKKQISLMB4/graph.json","events_json":"https://pith.science/api/pith-number/O5QVQ7PEJ755I4BNPKKQISLMB4/events.json","paper":"https://pith.science/paper/O5QVQ7PE"},"agent_actions":{"view_html":"https://pith.science/pith/O5QVQ7PEJ755I4BNPKKQISLMB4","download_json":"https://pith.science/pith/O5QVQ7PEJ755I4BNPKKQISLMB4.json","view_paper":"https://pith.science/paper/O5QVQ7PE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.06817&json=true","fetch_graph":"https://pith.science/api/pith-number/O5QVQ7PEJ755I4BNPKKQISLMB4/graph.json","fetch_events":"https://pith.science/api/pith-number/O5QVQ7PEJ755I4BNPKKQISLMB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5QVQ7PEJ755I4BNPKKQISLMB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5QVQ7PEJ755I4BNPKKQISLMB4/action/storage_attestation","attest_author":"https://pith.science/pith/O5QVQ7PEJ755I4BNPKKQISLMB4/action/author_attestation","sign_citation":"https://pith.science/pith/O5QVQ7PEJ755I4BNPKKQISLMB4/action/citation_signature","submit_replication":"https://pith.science/pith/O5QVQ7PEJ755I4BNPKKQISLMB4/action/replication_record"}},"created_at":"2026-07-05T05:11:37.082813+00:00","updated_at":"2026-07-05T05:11:37.082813+00:00"}