{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WAL63NAZGKJMWNP7IPRTV4SLIZ","short_pith_number":"pith:WAL63NAZ","schema_version":"1.0","canonical_sha256":"b017edb4193292cb35ff43e33af24b4668bbc7ce5d19afdcf7d7826a44ea2189","source":{"kind":"arxiv","id":"1811.10080","version":1},"attestation_state":"computed","paper":{"title":"Learning to discover and localize visual objects with open vocabulary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adriana Kovashka, Danfeng Qin, Jesse Berent, Keren Ye, Mingda Zhang, Wei Li","submitted_at":"2018-11-25T19:55:33Z","abstract_excerpt":"To alleviate the cost of obtaining accurate bounding boxes for training today's state-of-the-art object detection models, recent weakly supervised detection work has proposed techniques to learn from image-level labels. However, requiring discrete image-level labels is both restrictive and suboptimal. Real-world \"supervision\" usually consists of more unstructured text, such as captions. In this work we learn association maps between images and captions. We then use a novel objectness criterion to rank the resulting candidate boxes, such that high-ranking boxes have strong gradients along all e"},"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":"1811.10080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-25T19:55:33Z","cross_cats_sorted":[],"title_canon_sha256":"77be8859532b53c218958f9ec92285ef06da0ec046822768442b19d58a361a15","abstract_canon_sha256":"79a208ba7457260a907bdcffc3cecfd4422487a1bf8380424e91c842719273e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:58.724882Z","signature_b64":"v+4cTERBrccPPOVKEPZldwUP5LX/YoQEDcBcApimVrJ085hSZZ+vxEtrlt9zN+bHiLEVXOZiVQkskntd94jYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b017edb4193292cb35ff43e33af24b4668bbc7ce5d19afdcf7d7826a44ea2189","last_reissued_at":"2026-05-17T23:59:58.724445Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:58.724445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to discover and localize visual objects with open vocabulary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adriana Kovashka, Danfeng Qin, Jesse Berent, Keren Ye, Mingda Zhang, Wei Li","submitted_at":"2018-11-25T19:55:33Z","abstract_excerpt":"To alleviate the cost of obtaining accurate bounding boxes for training today's state-of-the-art object detection models, recent weakly supervised detection work has proposed techniques to learn from image-level labels. However, requiring discrete image-level labels is both restrictive and suboptimal. Real-world \"supervision\" usually consists of more unstructured text, such as captions. In this work we learn association maps between images and captions. We then use a novel objectness criterion to rank the resulting candidate boxes, such that high-ranking boxes have strong gradients along all e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10080","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":"1811.10080","created_at":"2026-05-17T23:59:58.724514+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.10080v1","created_at":"2026-05-17T23:59:58.724514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10080","created_at":"2026-05-17T23:59:58.724514+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAL63NAZGKJM","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAL63NAZGKJMWNP7","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAL63NAZ","created_at":"2026-05-18T12:32:59.047623+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/WAL63NAZGKJMWNP7IPRTV4SLIZ","json":"https://pith.science/pith/WAL63NAZGKJMWNP7IPRTV4SLIZ.json","graph_json":"https://pith.science/api/pith-number/WAL63NAZGKJMWNP7IPRTV4SLIZ/graph.json","events_json":"https://pith.science/api/pith-number/WAL63NAZGKJMWNP7IPRTV4SLIZ/events.json","paper":"https://pith.science/paper/WAL63NAZ"},"agent_actions":{"view_html":"https://pith.science/pith/WAL63NAZGKJMWNP7IPRTV4SLIZ","download_json":"https://pith.science/pith/WAL63NAZGKJMWNP7IPRTV4SLIZ.json","view_paper":"https://pith.science/paper/WAL63NAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.10080&json=true","fetch_graph":"https://pith.science/api/pith-number/WAL63NAZGKJMWNP7IPRTV4SLIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WAL63NAZGKJMWNP7IPRTV4SLIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAL63NAZGKJMWNP7IPRTV4SLIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAL63NAZGKJMWNP7IPRTV4SLIZ/action/storage_attestation","attest_author":"https://pith.science/pith/WAL63NAZGKJMWNP7IPRTV4SLIZ/action/author_attestation","sign_citation":"https://pith.science/pith/WAL63NAZGKJMWNP7IPRTV4SLIZ/action/citation_signature","submit_replication":"https://pith.science/pith/WAL63NAZGKJMWNP7IPRTV4SLIZ/action/replication_record"}},"created_at":"2026-05-17T23:59:58.724514+00:00","updated_at":"2026-05-17T23:59:58.724514+00:00"}