{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7OZDLKL3WEEMIXH2ST24NYQPFM","short_pith_number":"pith:7OZDLKL3","schema_version":"1.0","canonical_sha256":"fbb235a97bb108c45cfa94f5c6e20f2b1f231571c5e3152c64fba328e152afa8","source":{"kind":"arxiv","id":"2403.11120","version":2},"attestation_state":"computed","paper":{"title":"Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Seokju Cho, Seungryong Kim, Stephen Lin, Sunghwan Hong","submitted_at":"2024-03-17T07:02:55Z","abstract_excerpt":"This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. In the context of dense matching, many works benefit from one of two forms of aggregation: feature aggregation, which pertains to the alignment of similar features, or cost aggregation, a procedure aimed at instilling coherence in the flow estimates across neighboring pixels. In this work, we first show that feature aggregation and cost aggregation exhibit distinct characteristics and reveal the potential for substantial benefits stemming from the judicious use of both "},"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":"2403.11120","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T07:02:55Z","cross_cats_sorted":[],"title_canon_sha256":"c5135444433bb911ec4b62ffbdd38346d4cf862c66c1516b840d7d1ca3f08306","abstract_canon_sha256":"cd1baaeefba53ce7e4399c88ce9a483506fd4502dcd72092650da01f527afb97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:24.993894Z","signature_b64":"/6TwW9lOeEqmbt1WZpS9WQaC+/JSghnvl2rz6tY6WLgj2p7U3TFhfPOv0PU9YDjy91ztXwL3KEsgE7BRX6jnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbb235a97bb108c45cfa94f5c6e20f2b1f231571c5e3152c64fba328e152afa8","last_reissued_at":"2026-07-05T08:10:24.993447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:24.993447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Seokju Cho, Seungryong Kim, Stephen Lin, Sunghwan Hong","submitted_at":"2024-03-17T07:02:55Z","abstract_excerpt":"This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. In the context of dense matching, many works benefit from one of two forms of aggregation: feature aggregation, which pertains to the alignment of similar features, or cost aggregation, a procedure aimed at instilling coherence in the flow estimates across neighboring pixels. In this work, we first show that feature aggregation and cost aggregation exhibit distinct characteristics and reveal the potential for substantial benefits stemming from the judicious use of both "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11120","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/2403.11120/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":"2403.11120","created_at":"2026-07-05T08:10:24.993503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11120v2","created_at":"2026-07-05T08:10:24.993503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11120","created_at":"2026-07-05T08:10:24.993503+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OZDLKL3WEEM","created_at":"2026-07-05T08:10:24.993503+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OZDLKL3WEEMIXH2","created_at":"2026-07-05T08:10:24.993503+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OZDLKL3","created_at":"2026-07-05T08:10:24.993503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.04021","citing_title":"C3G: Learning Compact 3D Representations with 2K Gaussians","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04050","citing_title":"TORA: Topological Representation Alignment for 3D Shape Assembly","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08456","citing_title":"Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7OZDLKL3WEEMIXH2ST24NYQPFM","json":"https://pith.science/pith/7OZDLKL3WEEMIXH2ST24NYQPFM.json","graph_json":"https://pith.science/api/pith-number/7OZDLKL3WEEMIXH2ST24NYQPFM/graph.json","events_json":"https://pith.science/api/pith-number/7OZDLKL3WEEMIXH2ST24NYQPFM/events.json","paper":"https://pith.science/paper/7OZDLKL3"},"agent_actions":{"view_html":"https://pith.science/pith/7OZDLKL3WEEMIXH2ST24NYQPFM","download_json":"https://pith.science/pith/7OZDLKL3WEEMIXH2ST24NYQPFM.json","view_paper":"https://pith.science/paper/7OZDLKL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11120&json=true","fetch_graph":"https://pith.science/api/pith-number/7OZDLKL3WEEMIXH2ST24NYQPFM/graph.json","fetch_events":"https://pith.science/api/pith-number/7OZDLKL3WEEMIXH2ST24NYQPFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OZDLKL3WEEMIXH2ST24NYQPFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OZDLKL3WEEMIXH2ST24NYQPFM/action/storage_attestation","attest_author":"https://pith.science/pith/7OZDLKL3WEEMIXH2ST24NYQPFM/action/author_attestation","sign_citation":"https://pith.science/pith/7OZDLKL3WEEMIXH2ST24NYQPFM/action/citation_signature","submit_replication":"https://pith.science/pith/7OZDLKL3WEEMIXH2ST24NYQPFM/action/replication_record"}},"created_at":"2026-07-05T08:10:24.993503+00:00","updated_at":"2026-07-05T08:10:24.993503+00:00"}