{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TSCVPRRSHVVMQTSVMXBZ7PLJUY","short_pith_number":"pith:TSCVPRRS","schema_version":"1.0","canonical_sha256":"9c8557c6323d6ac84e5565c39fbd69a635f9c67634a02002bc97c262eb46da17","source":{"kind":"arxiv","id":"2204.00442","version":1},"attestation_state":"computed","paper":{"title":"Marginal Contrastive Correspondence for Guided Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Changgong Zhang, Fangneng Zhan, Jiahui Zhang, Rongliang Wu, Shijian Lu, Yingchen Yu","submitted_at":"2022-04-01T13:55:44Z","abstract_excerpt":"Exemplar-based image translation establishes dense correspondences between a conditional input and an exemplar (from two different domains) for leveraging detailed exemplar styles to achieve realistic image translation. Existing work builds the cross-domain correspondences implicitly by minimizing feature-wise distances across the two domains. Without explicit exploitation of domain-invariant features, this approach may not reduce the domain gap effectively which often leads to sub-optimal correspondences and image translation. We design a Marginal Contrastive Learning Network (MCL-Net) that e"},"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":"2204.00442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-01T13:55:44Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"8cd8f6372e4be842c40dad4ea5b84e579a469cfb40ae0a345a5802463ee540cb","abstract_canon_sha256":"b106f0b0579396409349f0e462e3eedf755f21d1a3a2d659323e4a2502e84c32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:47.326723Z","signature_b64":"ikzlyEkvRXq0LkSBSGQkqkw4ZFCDHRZo4yD8ZKR8jwqqix+I/3PosSc2nv3HVMvz/18eE9v7HJ0cSHCgSu1YDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c8557c6323d6ac84e5565c39fbd69a635f9c67634a02002bc97c262eb46da17","last_reissued_at":"2026-07-05T04:10:47.326291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:47.326291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Marginal Contrastive Correspondence for Guided Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Changgong Zhang, Fangneng Zhan, Jiahui Zhang, Rongliang Wu, Shijian Lu, Yingchen Yu","submitted_at":"2022-04-01T13:55:44Z","abstract_excerpt":"Exemplar-based image translation establishes dense correspondences between a conditional input and an exemplar (from two different domains) for leveraging detailed exemplar styles to achieve realistic image translation. Existing work builds the cross-domain correspondences implicitly by minimizing feature-wise distances across the two domains. Without explicit exploitation of domain-invariant features, this approach may not reduce the domain gap effectively which often leads to sub-optimal correspondences and image translation. We design a Marginal Contrastive Learning Network (MCL-Net) that e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00442","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.00442/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":"2204.00442","created_at":"2026-07-05T04:10:47.326366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.00442v1","created_at":"2026-07-05T04:10:47.326366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00442","created_at":"2026-07-05T04:10:47.326366+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSCVPRRSHVVM","created_at":"2026-07-05T04:10:47.326366+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSCVPRRSHVVMQTSV","created_at":"2026-07-05T04:10:47.326366+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSCVPRRS","created_at":"2026-07-05T04:10:47.326366+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/TSCVPRRSHVVMQTSVMXBZ7PLJUY","json":"https://pith.science/pith/TSCVPRRSHVVMQTSVMXBZ7PLJUY.json","graph_json":"https://pith.science/api/pith-number/TSCVPRRSHVVMQTSVMXBZ7PLJUY/graph.json","events_json":"https://pith.science/api/pith-number/TSCVPRRSHVVMQTSVMXBZ7PLJUY/events.json","paper":"https://pith.science/paper/TSCVPRRS"},"agent_actions":{"view_html":"https://pith.science/pith/TSCVPRRSHVVMQTSVMXBZ7PLJUY","download_json":"https://pith.science/pith/TSCVPRRSHVVMQTSVMXBZ7PLJUY.json","view_paper":"https://pith.science/paper/TSCVPRRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.00442&json=true","fetch_graph":"https://pith.science/api/pith-number/TSCVPRRSHVVMQTSVMXBZ7PLJUY/graph.json","fetch_events":"https://pith.science/api/pith-number/TSCVPRRSHVVMQTSVMXBZ7PLJUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSCVPRRSHVVMQTSVMXBZ7PLJUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSCVPRRSHVVMQTSVMXBZ7PLJUY/action/storage_attestation","attest_author":"https://pith.science/pith/TSCVPRRSHVVMQTSVMXBZ7PLJUY/action/author_attestation","sign_citation":"https://pith.science/pith/TSCVPRRSHVVMQTSVMXBZ7PLJUY/action/citation_signature","submit_replication":"https://pith.science/pith/TSCVPRRSHVVMQTSVMXBZ7PLJUY/action/replication_record"}},"created_at":"2026-07-05T04:10:47.326366+00:00","updated_at":"2026-07-05T04:10:47.326366+00:00"}