{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EYLYDGAKKZQ7EE3NXM3SAT62SC","short_pith_number":"pith:EYLYDGAK","schema_version":"1.0","canonical_sha256":"261781980a5661f2136dbb37204fda90bbaaaf0118096fd5dc0a75552d5df63c","source":{"kind":"arxiv","id":"1808.01244","version":2},"attestation_state":"computed","paper":{"title":"CornerNet: Detecting Objects as Paired Keypoints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hei Law, Jia Deng","submitted_at":"2018-08-03T16:05:55Z","abstract_excerpt":"We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network. By detecting objects as paired keypoints, we eliminate the need for designing a set of anchor boxes commonly used in prior single-stage detectors. In addition to our novel formulation, we introduce corner pooling, a new type of pooling layer that helps the network better localize corners. Experiments show that CornerNet achieves a 42.2% AP on MS COCO, outperforming all existing one-sta"},"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":"1808.01244","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-03T16:05:55Z","cross_cats_sorted":[],"title_canon_sha256":"d4ace4c7cebd6719a5a6cc7ce1dd4e80f6ca7496037cc9e70d4e366a5ef3f5c4","abstract_canon_sha256":"9e2b31b137a63f453fb8c342cd67e08a42592dd6c4271452abfe869a06e2295d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:59.526698Z","signature_b64":"4RRqp8FzkOLOnacHIJW2klQjaZcpIONnIVkzk07IYwusO2WGLF+C2pmgqiZeb67oUOiF9t4DlPHCrq9SScHjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"261781980a5661f2136dbb37204fda90bbaaaf0118096fd5dc0a75552d5df63c","last_reissued_at":"2026-05-17T23:50:59.526143Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:59.526143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CornerNet: Detecting Objects as Paired Keypoints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hei Law, Jia Deng","submitted_at":"2018-08-03T16:05:55Z","abstract_excerpt":"We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network. By detecting objects as paired keypoints, we eliminate the need for designing a set of anchor boxes commonly used in prior single-stage detectors. In addition to our novel formulation, we introduce corner pooling, a new type of pooling layer that helps the network better localize corners. Experiments show that CornerNet achieves a 42.2% AP on MS COCO, outperforming all existing one-sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01244","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":"1808.01244","created_at":"2026-05-17T23:50:59.526234+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.01244v2","created_at":"2026-05-17T23:50:59.526234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01244","created_at":"2026-05-17T23:50:59.526234+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYLYDGAKKZQ7","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYLYDGAKKZQ7EE3N","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYLYDGAK","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08339","citing_title":"SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYLYDGAKKZQ7EE3NXM3SAT62SC","json":"https://pith.science/pith/EYLYDGAKKZQ7EE3NXM3SAT62SC.json","graph_json":"https://pith.science/api/pith-number/EYLYDGAKKZQ7EE3NXM3SAT62SC/graph.json","events_json":"https://pith.science/api/pith-number/EYLYDGAKKZQ7EE3NXM3SAT62SC/events.json","paper":"https://pith.science/paper/EYLYDGAK"},"agent_actions":{"view_html":"https://pith.science/pith/EYLYDGAKKZQ7EE3NXM3SAT62SC","download_json":"https://pith.science/pith/EYLYDGAKKZQ7EE3NXM3SAT62SC.json","view_paper":"https://pith.science/paper/EYLYDGAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.01244&json=true","fetch_graph":"https://pith.science/api/pith-number/EYLYDGAKKZQ7EE3NXM3SAT62SC/graph.json","fetch_events":"https://pith.science/api/pith-number/EYLYDGAKKZQ7EE3NXM3SAT62SC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYLYDGAKKZQ7EE3NXM3SAT62SC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYLYDGAKKZQ7EE3NXM3SAT62SC/action/storage_attestation","attest_author":"https://pith.science/pith/EYLYDGAKKZQ7EE3NXM3SAT62SC/action/author_attestation","sign_citation":"https://pith.science/pith/EYLYDGAKKZQ7EE3NXM3SAT62SC/action/citation_signature","submit_replication":"https://pith.science/pith/EYLYDGAKKZQ7EE3NXM3SAT62SC/action/replication_record"}},"created_at":"2026-05-17T23:50:59.526234+00:00","updated_at":"2026-05-17T23:50:59.526234+00:00"}