{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TZBT2WNSFJBD5W2Y5624BJRJAV","short_pith_number":"pith:TZBT2WNS","schema_version":"1.0","canonical_sha256":"9e433d59b22a423edb58efb5c0a629055ecd33d2291c2e259262517454e5a400","source":{"kind":"arxiv","id":"1704.04749","version":1},"attestation_state":"computed","paper":{"title":"AnchorNet: A Weakly Supervised Network to Learn Geometry-sensitive Features For Semantic Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, David Novotny, Diane Larlus","submitted_at":"2017-04-16T11:07:02Z","abstract_excerpt":"Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG. We argue that the strong invariance properties that are key to the success of recent deep architectures on the classification task make them unfit for dense correspondence tasks, unless a large amount of supervision is used. In this work, we propose a deep network, termed AnchorNet, that produces image representations that are well-suited for semantic matching. It relies on a set of filters whose response is geometrically consistent across"},"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":"1704.04749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-16T11:07:02Z","cross_cats_sorted":[],"title_canon_sha256":"cb683862b9c4fd86ae3d4ffb2b70f4e065e451a108e0549f69c667b9491ab1cd","abstract_canon_sha256":"21e9dd4d666b22f716e8e231cc1f9be882ef2cb65d69702b4fb970dea07156ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:17.842408Z","signature_b64":"4pGVs5bIZxurip/BZZz3xUWQV3q6j8BwtzlKQ7aT2WjoNmR+DEMR5+w3Z6sIFG7LfCqvw1b8Sy4E9D/zUQ29CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e433d59b22a423edb58efb5c0a629055ecd33d2291c2e259262517454e5a400","last_reissued_at":"2026-05-18T00:46:17.842057Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:17.842057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnchorNet: A Weakly Supervised Network to Learn Geometry-sensitive Features For Semantic Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, David Novotny, Diane Larlus","submitted_at":"2017-04-16T11:07:02Z","abstract_excerpt":"Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG. We argue that the strong invariance properties that are key to the success of recent deep architectures on the classification task make them unfit for dense correspondence tasks, unless a large amount of supervision is used. In this work, we propose a deep network, termed AnchorNet, that produces image representations that are well-suited for semantic matching. It relies on a set of filters whose response is geometrically consistent across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04749","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":""},"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":"1704.04749","created_at":"2026-05-18T00:46:17.842111+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.04749v1","created_at":"2026-05-18T00:46:17.842111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04749","created_at":"2026-05-18T00:46:17.842111+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZBT2WNSFJBD","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZBT2WNSFJBD5W2Y","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZBT2WNS","created_at":"2026-05-18T12:31:46.661854+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/TZBT2WNSFJBD5W2Y5624BJRJAV","json":"https://pith.science/pith/TZBT2WNSFJBD5W2Y5624BJRJAV.json","graph_json":"https://pith.science/api/pith-number/TZBT2WNSFJBD5W2Y5624BJRJAV/graph.json","events_json":"https://pith.science/api/pith-number/TZBT2WNSFJBD5W2Y5624BJRJAV/events.json","paper":"https://pith.science/paper/TZBT2WNS"},"agent_actions":{"view_html":"https://pith.science/pith/TZBT2WNSFJBD5W2Y5624BJRJAV","download_json":"https://pith.science/pith/TZBT2WNSFJBD5W2Y5624BJRJAV.json","view_paper":"https://pith.science/paper/TZBT2WNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.04749&json=true","fetch_graph":"https://pith.science/api/pith-number/TZBT2WNSFJBD5W2Y5624BJRJAV/graph.json","fetch_events":"https://pith.science/api/pith-number/TZBT2WNSFJBD5W2Y5624BJRJAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZBT2WNSFJBD5W2Y5624BJRJAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZBT2WNSFJBD5W2Y5624BJRJAV/action/storage_attestation","attest_author":"https://pith.science/pith/TZBT2WNSFJBD5W2Y5624BJRJAV/action/author_attestation","sign_citation":"https://pith.science/pith/TZBT2WNSFJBD5W2Y5624BJRJAV/action/citation_signature","submit_replication":"https://pith.science/pith/TZBT2WNSFJBD5W2Y5624BJRJAV/action/replication_record"}},"created_at":"2026-05-18T00:46:17.842111+00:00","updated_at":"2026-05-18T00:46:17.842111+00:00"}