{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ORJNBVNMDWIPBQ2GW3VNRZWB3H","short_pith_number":"pith:ORJNBVNM","schema_version":"1.0","canonical_sha256":"7452d0d5ac1d90f0c346b6ead8e6c1d9d8e1d8659e92af72ec3bc7b2282835ac","source":{"kind":"arxiv","id":"1606.07770","version":3},"attestation_state":"computed","paper":{"title":"Captioning Images with Diverse Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Kate Saenko, Lisa Anne Hendricks, Marcus Rohrbach, Raymond Mooney, Subhashini Venugopalan, Trevor Darrell","submitted_at":"2016-06-24T17:53:45Z","abstract_excerpt":"Recent captioning models are limited in their ability to scale and describe concepts unseen in paired image-text corpora. We propose the Novel Object Captioner (NOC), a deep visual semantic captioning model that can describe a large number of object categories not present in existing image-caption datasets. Our model takes advantage of external sources -- labeled images from object recognition datasets, and semantic knowledge extracted from unannotated text. We propose minimizing a joint objective which can learn from these diverse data sources and leverage distributional semantic embeddings, "},"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":"1606.07770","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-24T17:53:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b1afc1a10d216ffc3a9597df6b7634b2cd47cf620514d14c7079987c1a27619b","abstract_canon_sha256":"d973bc711a387494d0c3b57cce282ee2eb132e64a1f3c2f34a18721fb6f7f245"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:52.974263Z","signature_b64":"DFpLj3E31RjEMk/lLQL+D6nyOJklJp2f7WFn5deqOSOXVMWbpq2x9xzCoFUmmYtWxZ55bGZIfcjPiFWAreGUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7452d0d5ac1d90f0c346b6ead8e6c1d9d8e1d8659e92af72ec3bc7b2282835ac","last_reissued_at":"2026-05-18T00:39:52.973639Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:52.973639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Captioning Images with Diverse Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Kate Saenko, Lisa Anne Hendricks, Marcus Rohrbach, Raymond Mooney, Subhashini Venugopalan, Trevor Darrell","submitted_at":"2016-06-24T17:53:45Z","abstract_excerpt":"Recent captioning models are limited in their ability to scale and describe concepts unseen in paired image-text corpora. We propose the Novel Object Captioner (NOC), a deep visual semantic captioning model that can describe a large number of object categories not present in existing image-caption datasets. Our model takes advantage of external sources -- labeled images from object recognition datasets, and semantic knowledge extracted from unannotated text. We propose minimizing a joint objective which can learn from these diverse data sources and leverage distributional semantic embeddings, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07770","kind":"arxiv","version":3},"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":"1606.07770","created_at":"2026-05-18T00:39:52.973734+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.07770v3","created_at":"2026-05-18T00:39:52.973734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07770","created_at":"2026-05-18T00:39:52.973734+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORJNBVNMDWIP","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORJNBVNMDWIPBQ2G","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORJNBVNM","created_at":"2026-05-18T12:30:36.002864+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/ORJNBVNMDWIPBQ2GW3VNRZWB3H","json":"https://pith.science/pith/ORJNBVNMDWIPBQ2GW3VNRZWB3H.json","graph_json":"https://pith.science/api/pith-number/ORJNBVNMDWIPBQ2GW3VNRZWB3H/graph.json","events_json":"https://pith.science/api/pith-number/ORJNBVNMDWIPBQ2GW3VNRZWB3H/events.json","paper":"https://pith.science/paper/ORJNBVNM"},"agent_actions":{"view_html":"https://pith.science/pith/ORJNBVNMDWIPBQ2GW3VNRZWB3H","download_json":"https://pith.science/pith/ORJNBVNMDWIPBQ2GW3VNRZWB3H.json","view_paper":"https://pith.science/paper/ORJNBVNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.07770&json=true","fetch_graph":"https://pith.science/api/pith-number/ORJNBVNMDWIPBQ2GW3VNRZWB3H/graph.json","fetch_events":"https://pith.science/api/pith-number/ORJNBVNMDWIPBQ2GW3VNRZWB3H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORJNBVNMDWIPBQ2GW3VNRZWB3H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORJNBVNMDWIPBQ2GW3VNRZWB3H/action/storage_attestation","attest_author":"https://pith.science/pith/ORJNBVNMDWIPBQ2GW3VNRZWB3H/action/author_attestation","sign_citation":"https://pith.science/pith/ORJNBVNMDWIPBQ2GW3VNRZWB3H/action/citation_signature","submit_replication":"https://pith.science/pith/ORJNBVNMDWIPBQ2GW3VNRZWB3H/action/replication_record"}},"created_at":"2026-05-18T00:39:52.973734+00:00","updated_at":"2026-05-18T00:39:52.973734+00:00"}