{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KFD7GQYODLPAW6PGHNO4IRICXD","short_pith_number":"pith:KFD7GQYO","schema_version":"1.0","canonical_sha256":"5147f3430e1ade0b79e63b5dc44502b8c0f7218374a1dca12dd8f827a4e0e492","source":{"kind":"arxiv","id":"1802.01777","version":2},"attestation_state":"computed","paper":{"title":"Brute-Force Facial Landmark Analysis With A 140,000-Way Classifier","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deva Ramanan, Laszlo Jeni, Mengtian Li","submitted_at":"2018-02-06T03:20:41Z","abstract_excerpt":"We propose a simple approach to visual alignment, focusing on the illustrative task of facial landmark estimation. While most prior work treats this as a regression problem, we instead formulate it as a discrete $K$-way classification task, where a classifier is trained to return one of $K$ discrete alignments. One crucial benefit of a classifier is the ability to report back a (softmax) distribution over putative alignments. We demonstrate that this distribution is a rich representation that can be marginalized (to generate uncertainty estimates over groups of landmarks) and conditioned on (t"},"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":"1802.01777","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-06T03:20:41Z","cross_cats_sorted":[],"title_canon_sha256":"20e3b856d30a6eed377d555c4b99f015232fbd8abf37e57f61117d560ccb0c77","abstract_canon_sha256":"13165bf88328c77948651fe29b903881616a0a9f701b672441e4b3562a53eb8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:20.735424Z","signature_b64":"fn0cBS00fHDW8VGZ7zeJV5Lc3HL4mDEDfYwK/YOyH4uVd026MQbdF4sNTPmL28NjjQb8knWDXc8BIcygSgbiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5147f3430e1ade0b79e63b5dc44502b8c0f7218374a1dca12dd8f827a4e0e492","last_reissued_at":"2026-05-18T00:23:20.734547Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:20.734547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Brute-Force Facial Landmark Analysis With A 140,000-Way Classifier","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deva Ramanan, Laszlo Jeni, Mengtian Li","submitted_at":"2018-02-06T03:20:41Z","abstract_excerpt":"We propose a simple approach to visual alignment, focusing on the illustrative task of facial landmark estimation. While most prior work treats this as a regression problem, we instead formulate it as a discrete $K$-way classification task, where a classifier is trained to return one of $K$ discrete alignments. One crucial benefit of a classifier is the ability to report back a (softmax) distribution over putative alignments. We demonstrate that this distribution is a rich representation that can be marginalized (to generate uncertainty estimates over groups of landmarks) and conditioned on (t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.01777","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":""},"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":"1802.01777","created_at":"2026-05-18T00:23:20.734706+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.01777v2","created_at":"2026-05-18T00:23:20.734706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.01777","created_at":"2026-05-18T00:23:20.734706+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFD7GQYODLPA","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFD7GQYODLPAW6PG","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFD7GQYO","created_at":"2026-05-18T12:32:33.847187+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/KFD7GQYODLPAW6PGHNO4IRICXD","json":"https://pith.science/pith/KFD7GQYODLPAW6PGHNO4IRICXD.json","graph_json":"https://pith.science/api/pith-number/KFD7GQYODLPAW6PGHNO4IRICXD/graph.json","events_json":"https://pith.science/api/pith-number/KFD7GQYODLPAW6PGHNO4IRICXD/events.json","paper":"https://pith.science/paper/KFD7GQYO"},"agent_actions":{"view_html":"https://pith.science/pith/KFD7GQYODLPAW6PGHNO4IRICXD","download_json":"https://pith.science/pith/KFD7GQYODLPAW6PGHNO4IRICXD.json","view_paper":"https://pith.science/paper/KFD7GQYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.01777&json=true","fetch_graph":"https://pith.science/api/pith-number/KFD7GQYODLPAW6PGHNO4IRICXD/graph.json","fetch_events":"https://pith.science/api/pith-number/KFD7GQYODLPAW6PGHNO4IRICXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFD7GQYODLPAW6PGHNO4IRICXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFD7GQYODLPAW6PGHNO4IRICXD/action/storage_attestation","attest_author":"https://pith.science/pith/KFD7GQYODLPAW6PGHNO4IRICXD/action/author_attestation","sign_citation":"https://pith.science/pith/KFD7GQYODLPAW6PGHNO4IRICXD/action/citation_signature","submit_replication":"https://pith.science/pith/KFD7GQYODLPAW6PGHNO4IRICXD/action/replication_record"}},"created_at":"2026-05-18T00:23:20.734706+00:00","updated_at":"2026-05-18T00:23:20.734706+00:00"}