{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SL3SACPNSLRRTOA6P5DRWG7VB2","short_pith_number":"pith:SL3SACPN","schema_version":"1.0","canonical_sha256":"92f72009ed92e319b81e7f471b1bf50ea3bc746581b28b52b39442872603501b","source":{"kind":"arxiv","id":"1908.06537","version":1},"attestation_state":"computed","paper":{"title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jean Ponce, Jongmin Lee, Juhong Min, Minsu Cho","submitted_at":"2019-08-18T23:23:54Z","abstract_excerpt":"Establishing visual correspondences under large intra-class variations requires analyzing images at different levels, from features linked to semantics and context to local patterns, while being invariant to instance-specific details. To tackle these challenges, we represent images by \"hyperpixels\" that leverage a small number of relevant features selected among early to late layers of a convolutional neural network. Taking advantage of the condensed features of hyperpixels, we develop an effective real-time matching algorithm based on Hough geometric voting. The proposed method, hyperpixel fl"},"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":"1908.06537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-18T23:23:54Z","cross_cats_sorted":[],"title_canon_sha256":"fa19cc395b48f6bd20d99f024d6ef0d8372c00680a7b0d5c8d3db4f687f875ce","abstract_canon_sha256":"2c8c46e41c4d87ded26f6b29309670079b8e6d1e45135c12679cada3d3f3d5a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:16.923022Z","signature_b64":"z+jdKL7xSSyfxinlUMXyaBl+0ksO2U/VmbalhTFviyqg2y2KmjQNzGK0TvqkQu6/RvBpYuhvEnzQ7XV9EVgEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92f72009ed92e319b81e7f471b1bf50ea3bc746581b28b52b39442872603501b","last_reissued_at":"2026-07-04T23:58:16.922689Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:16.922689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jean Ponce, Jongmin Lee, Juhong Min, Minsu Cho","submitted_at":"2019-08-18T23:23:54Z","abstract_excerpt":"Establishing visual correspondences under large intra-class variations requires analyzing images at different levels, from features linked to semantics and context to local patterns, while being invariant to instance-specific details. To tackle these challenges, we represent images by \"hyperpixels\" that leverage a small number of relevant features selected among early to late layers of a convolutional neural network. Taking advantage of the condensed features of hyperpixels, we develop an effective real-time matching algorithm based on Hough geometric voting. The proposed method, hyperpixel fl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06537","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/1908.06537/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":"1908.06537","created_at":"2026-07-04T23:58:16.922744+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.06537v1","created_at":"2026-07-04T23:58:16.922744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06537","created_at":"2026-07-04T23:58:16.922744+00:00"},{"alias_kind":"pith_short_12","alias_value":"SL3SACPNSLRR","created_at":"2026-07-04T23:58:16.922744+00:00"},{"alias_kind":"pith_short_16","alias_value":"SL3SACPNSLRRTOA6","created_at":"2026-07-04T23:58:16.922744+00:00"},{"alias_kind":"pith_short_8","alias_value":"SL3SACPN","created_at":"2026-07-04T23:58:16.922744+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/SL3SACPNSLRRTOA6P5DRWG7VB2","json":"https://pith.science/pith/SL3SACPNSLRRTOA6P5DRWG7VB2.json","graph_json":"https://pith.science/api/pith-number/SL3SACPNSLRRTOA6P5DRWG7VB2/graph.json","events_json":"https://pith.science/api/pith-number/SL3SACPNSLRRTOA6P5DRWG7VB2/events.json","paper":"https://pith.science/paper/SL3SACPN"},"agent_actions":{"view_html":"https://pith.science/pith/SL3SACPNSLRRTOA6P5DRWG7VB2","download_json":"https://pith.science/pith/SL3SACPNSLRRTOA6P5DRWG7VB2.json","view_paper":"https://pith.science/paper/SL3SACPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.06537&json=true","fetch_graph":"https://pith.science/api/pith-number/SL3SACPNSLRRTOA6P5DRWG7VB2/graph.json","fetch_events":"https://pith.science/api/pith-number/SL3SACPNSLRRTOA6P5DRWG7VB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SL3SACPNSLRRTOA6P5DRWG7VB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SL3SACPNSLRRTOA6P5DRWG7VB2/action/storage_attestation","attest_author":"https://pith.science/pith/SL3SACPNSLRRTOA6P5DRWG7VB2/action/author_attestation","sign_citation":"https://pith.science/pith/SL3SACPNSLRRTOA6P5DRWG7VB2/action/citation_signature","submit_replication":"https://pith.science/pith/SL3SACPNSLRRTOA6P5DRWG7VB2/action/replication_record"}},"created_at":"2026-07-04T23:58:16.922744+00:00","updated_at":"2026-07-04T23:58:16.922744+00:00"}