{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KGFMARJ426ONA7XTEPYUU5IYFM","short_pith_number":"pith:KGFMARJ4","schema_version":"1.0","canonical_sha256":"518ac0453cd79cd07ef323f14a75182b245a3826801a2cbcbb0f29f54f9c6193","source":{"kind":"arxiv","id":"2204.02958","version":1},"attestation_state":"computed","paper":{"title":"LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Atrishi, R. Venkatesh Babu, Sai Sree Harsha, Susmit Agrawal, Tejan Karmali, Varun Jampani","submitted_at":"2022-04-06T17:48:18Z","abstract_excerpt":"In this work, we introduce LEAD, an approach to discover landmarks from an unannotated collection of category-specific images. Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image, which are further used to learn landmarks in a semi-supervised manner. While there have been advances in self-supervised learning of image features for instance-level tasks like classification, these methods do not ensure dense equivariant representations. The property of equivariance is of interest for dense prediction tasks like landma"},"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":"2204.02958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-06T17:48:18Z","cross_cats_sorted":[],"title_canon_sha256":"54b70efa5a35a44fe763475a80e2e91edb41b2fa155984d4da62ba605954a747","abstract_canon_sha256":"2c0295fbb88583e6228aa56cfeae88fed2ccf7960784ef2396c91fc94a93152f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:14.001825Z","signature_b64":"vQDAs2QDuCbbidfSLVmeOYzvJcEOCRJ/zY5ShdYelTfQN9DWCzmdxUNJMvPaIcr86tFZuWeaS1fVzMgMyIiDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"518ac0453cd79cd07ef323f14a75182b245a3826801a2cbcbb0f29f54f9c6193","last_reissued_at":"2026-07-05T04:12:14.001480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:14.001480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Atrishi, R. Venkatesh Babu, Sai Sree Harsha, Susmit Agrawal, Tejan Karmali, Varun Jampani","submitted_at":"2022-04-06T17:48:18Z","abstract_excerpt":"In this work, we introduce LEAD, an approach to discover landmarks from an unannotated collection of category-specific images. Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image, which are further used to learn landmarks in a semi-supervised manner. While there have been advances in self-supervised learning of image features for instance-level tasks like classification, these methods do not ensure dense equivariant representations. The property of equivariance is of interest for dense prediction tasks like landma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02958","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/2204.02958/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":"2204.02958","created_at":"2026-07-05T04:12:14.001542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.02958v1","created_at":"2026-07-05T04:12:14.001542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02958","created_at":"2026-07-05T04:12:14.001542+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGFMARJ426ON","created_at":"2026-07-05T04:12:14.001542+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGFMARJ426ONA7XT","created_at":"2026-07-05T04:12:14.001542+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGFMARJ4","created_at":"2026-07-05T04:12:14.001542+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/KGFMARJ426ONA7XTEPYUU5IYFM","json":"https://pith.science/pith/KGFMARJ426ONA7XTEPYUU5IYFM.json","graph_json":"https://pith.science/api/pith-number/KGFMARJ426ONA7XTEPYUU5IYFM/graph.json","events_json":"https://pith.science/api/pith-number/KGFMARJ426ONA7XTEPYUU5IYFM/events.json","paper":"https://pith.science/paper/KGFMARJ4"},"agent_actions":{"view_html":"https://pith.science/pith/KGFMARJ426ONA7XTEPYUU5IYFM","download_json":"https://pith.science/pith/KGFMARJ426ONA7XTEPYUU5IYFM.json","view_paper":"https://pith.science/paper/KGFMARJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.02958&json=true","fetch_graph":"https://pith.science/api/pith-number/KGFMARJ426ONA7XTEPYUU5IYFM/graph.json","fetch_events":"https://pith.science/api/pith-number/KGFMARJ426ONA7XTEPYUU5IYFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGFMARJ426ONA7XTEPYUU5IYFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGFMARJ426ONA7XTEPYUU5IYFM/action/storage_attestation","attest_author":"https://pith.science/pith/KGFMARJ426ONA7XTEPYUU5IYFM/action/author_attestation","sign_citation":"https://pith.science/pith/KGFMARJ426ONA7XTEPYUU5IYFM/action/citation_signature","submit_replication":"https://pith.science/pith/KGFMARJ426ONA7XTEPYUU5IYFM/action/replication_record"}},"created_at":"2026-07-05T04:12:14.001542+00:00","updated_at":"2026-07-05T04:12:14.001542+00:00"}