{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:XA2S5ZCRJIUTF2TXP4XHD4RHB4","short_pith_number":"pith:XA2S5ZCR","schema_version":"1.0","canonical_sha256":"b8352ee4514a2932ea777f2e71f2270f3145cdb567be969ff503bb46e98a3211","source":{"kind":"arxiv","id":"1701.06171","version":4},"attestation_state":"computed","paper":{"title":"Greedy Structure Learning of Hierarchical Compositional Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Kortylewski, Aleksander Wieczorek, Andreas Morel-Forster, Clemens Blumer, Mario Wieser, Sonali Parbhoo, Thomas Vetter, Volker Roth","submitted_at":"2017-01-22T14:56:31Z","abstract_excerpt":"In this work, we consider the problem of learning a hierarchical generative model of an object from a set of images which show examples of the object in the presence of variable background clutter. Existing approaches to this problem are limited by making strong a-priori assumptions about the object's geometric structure and require segmented training data for learning. In this paper, we propose a novel framework for learning hierarchical compositional models (HCMs) which do not suffer from the mentioned limitations. We present a generalized formulation of HCMs and describe a greedy structure "},"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":"1701.06171","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-22T14:56:31Z","cross_cats_sorted":[],"title_canon_sha256":"9db616ce0117b8629336d189fa9626700a3a983f25c198bb608e97e0afc4f3d6","abstract_canon_sha256":"94a1d08223f295ea56cbefad68340caba2a1cfdce5931afe80296c8a86f2006a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:41.032774Z","signature_b64":"fJyr9BQVkG4RoslmyvTvicIPTsdcw3gV16Xwsgo2o3mmweU4DgUzBT3vLXd+OvfOFEq8lLcBn6ZvpiYYPKIGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8352ee4514a2932ea777f2e71f2270f3145cdb567be969ff503bb46e98a3211","last_reissued_at":"2026-05-17T23:48:41.032197Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:41.032197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Greedy Structure Learning of Hierarchical Compositional Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Kortylewski, Aleksander Wieczorek, Andreas Morel-Forster, Clemens Blumer, Mario Wieser, Sonali Parbhoo, Thomas Vetter, Volker Roth","submitted_at":"2017-01-22T14:56:31Z","abstract_excerpt":"In this work, we consider the problem of learning a hierarchical generative model of an object from a set of images which show examples of the object in the presence of variable background clutter. Existing approaches to this problem are limited by making strong a-priori assumptions about the object's geometric structure and require segmented training data for learning. In this paper, we propose a novel framework for learning hierarchical compositional models (HCMs) which do not suffer from the mentioned limitations. We present a generalized formulation of HCMs and describe a greedy structure "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.06171","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1701.06171","created_at":"2026-05-17T23:48:41.032285+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.06171v4","created_at":"2026-05-17T23:48:41.032285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.06171","created_at":"2026-05-17T23:48:41.032285+00:00"},{"alias_kind":"pith_short_12","alias_value":"XA2S5ZCRJIUT","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"XA2S5ZCRJIUTF2TX","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"XA2S5ZCR","created_at":"2026-05-18T12:31:53.515858+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/XA2S5ZCRJIUTF2TXP4XHD4RHB4","json":"https://pith.science/pith/XA2S5ZCRJIUTF2TXP4XHD4RHB4.json","graph_json":"https://pith.science/api/pith-number/XA2S5ZCRJIUTF2TXP4XHD4RHB4/graph.json","events_json":"https://pith.science/api/pith-number/XA2S5ZCRJIUTF2TXP4XHD4RHB4/events.json","paper":"https://pith.science/paper/XA2S5ZCR"},"agent_actions":{"view_html":"https://pith.science/pith/XA2S5ZCRJIUTF2TXP4XHD4RHB4","download_json":"https://pith.science/pith/XA2S5ZCRJIUTF2TXP4XHD4RHB4.json","view_paper":"https://pith.science/paper/XA2S5ZCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.06171&json=true","fetch_graph":"https://pith.science/api/pith-number/XA2S5ZCRJIUTF2TXP4XHD4RHB4/graph.json","fetch_events":"https://pith.science/api/pith-number/XA2S5ZCRJIUTF2TXP4XHD4RHB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XA2S5ZCRJIUTF2TXP4XHD4RHB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XA2S5ZCRJIUTF2TXP4XHD4RHB4/action/storage_attestation","attest_author":"https://pith.science/pith/XA2S5ZCRJIUTF2TXP4XHD4RHB4/action/author_attestation","sign_citation":"https://pith.science/pith/XA2S5ZCRJIUTF2TXP4XHD4RHB4/action/citation_signature","submit_replication":"https://pith.science/pith/XA2S5ZCRJIUTF2TXP4XHD4RHB4/action/replication_record"}},"created_at":"2026-05-17T23:48:41.032285+00:00","updated_at":"2026-05-17T23:48:41.032285+00:00"}