{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6RLJVFV7QXYXC4AK55VHE7GXJC","short_pith_number":"pith:6RLJVFV7","schema_version":"1.0","canonical_sha256":"f4569a96bf85f171700aef6a727cd7488ecf9e0ea2a0d0c3c730eae9111a026f","source":{"kind":"arxiv","id":"2003.06788","version":2},"attestation_state":"computed","paper":{"title":"GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bruno Lepri, Jian Yao, Marco De Nadai, Nicu Sebe, Xavier Alameda-Pineda, Yahui Liu","submitted_at":"2020-03-15T10:18:56Z","abstract_excerpt":"Unsupervised image-to-image translation (UNIT) aims at learning a mapping between several visual domains by using unpaired training images. Recent studies have shown remarkable success for multiple domains but they suffer from two main limitations: they are either built from several two-domain mappings that are required to be learned independently, or they generate low-diversity results, a problem known as mode collapse. To overcome these limitations, we propose a method named GMM-UNIT, which is based on a content-attribute disentangled representation where the attribute space is fitted with a"},"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":"2003.06788","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-15T10:18:56Z","cross_cats_sorted":[],"title_canon_sha256":"cb4936f6923d3cb7ea5bd15d6e3425dc1f4042a062fc66bfc96c6d2d5f871242","abstract_canon_sha256":"b965a4fbdd7cc2f8e78ff09ff273c224ddd728b41ffbb192879c490d18651a19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:42.748881Z","signature_b64":"jqRUI7/xS/X3Wht2OzoFB0U8PLPIb56TwPfJ2pqB+r8CNWKJpVo05r1d6UOJ332GdG+yWe3TNJLY8NJFNWgyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4569a96bf85f171700aef6a727cd7488ecf9e0ea2a0d0c3c730eae9111a026f","last_reissued_at":"2026-07-05T00:49:42.748396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:42.748396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bruno Lepri, Jian Yao, Marco De Nadai, Nicu Sebe, Xavier Alameda-Pineda, Yahui Liu","submitted_at":"2020-03-15T10:18:56Z","abstract_excerpt":"Unsupervised image-to-image translation (UNIT) aims at learning a mapping between several visual domains by using unpaired training images. Recent studies have shown remarkable success for multiple domains but they suffer from two main limitations: they are either built from several two-domain mappings that are required to be learned independently, or they generate low-diversity results, a problem known as mode collapse. To overcome these limitations, we propose a method named GMM-UNIT, which is based on a content-attribute disentangled representation where the attribute space is fitted with a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.06788","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/2003.06788/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":"2003.06788","created_at":"2026-07-05T00:49:42.748455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.06788v2","created_at":"2026-07-05T00:49:42.748455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.06788","created_at":"2026-07-05T00:49:42.748455+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RLJVFV7QXYX","created_at":"2026-07-05T00:49:42.748455+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RLJVFV7QXYXC4AK","created_at":"2026-07-05T00:49:42.748455+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RLJVFV7","created_at":"2026-07-05T00:49:42.748455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06973","citing_title":"Free on the Fly: Enhancing Flexibility in Test-Time Adaptation with Online EM","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RLJVFV7QXYXC4AK55VHE7GXJC","json":"https://pith.science/pith/6RLJVFV7QXYXC4AK55VHE7GXJC.json","graph_json":"https://pith.science/api/pith-number/6RLJVFV7QXYXC4AK55VHE7GXJC/graph.json","events_json":"https://pith.science/api/pith-number/6RLJVFV7QXYXC4AK55VHE7GXJC/events.json","paper":"https://pith.science/paper/6RLJVFV7"},"agent_actions":{"view_html":"https://pith.science/pith/6RLJVFV7QXYXC4AK55VHE7GXJC","download_json":"https://pith.science/pith/6RLJVFV7QXYXC4AK55VHE7GXJC.json","view_paper":"https://pith.science/paper/6RLJVFV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.06788&json=true","fetch_graph":"https://pith.science/api/pith-number/6RLJVFV7QXYXC4AK55VHE7GXJC/graph.json","fetch_events":"https://pith.science/api/pith-number/6RLJVFV7QXYXC4AK55VHE7GXJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RLJVFV7QXYXC4AK55VHE7GXJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RLJVFV7QXYXC4AK55VHE7GXJC/action/storage_attestation","attest_author":"https://pith.science/pith/6RLJVFV7QXYXC4AK55VHE7GXJC/action/author_attestation","sign_citation":"https://pith.science/pith/6RLJVFV7QXYXC4AK55VHE7GXJC/action/citation_signature","submit_replication":"https://pith.science/pith/6RLJVFV7QXYXC4AK55VHE7GXJC/action/replication_record"}},"created_at":"2026-07-05T00:49:42.748455+00:00","updated_at":"2026-07-05T00:49:42.748455+00:00"}