{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:Y6VU7TPHBPXKX2HKWGHHV7DPY4","short_pith_number":"pith:Y6VU7TPH","schema_version":"1.0","canonical_sha256":"c7ab4fcde70beeabe8eab18e7afc6fc705fc8d5375a2cd00c683dc341876e806","source":{"kind":"arxiv","id":"1511.07571","version":1},"attestation_state":"computed","paper":{"title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrej Karpathy, Justin Johnson, Li Fei-Fei","submitted_at":"2015-11-24T05:13:54Z","abstract_excerpt":"We introduce the dense captioning task, which requires a computer vision system to both localize and describe salient regions in images in natural language. The dense captioning task generalizes object detection when the descriptions consist of a single word, and Image Captioning when one predicted region covers the full image. To address the localization and description task jointly we propose a Fully Convolutional Localization Network (FCLN) architecture that processes an image with a single, efficient forward pass, requires no external regions proposals, and can be trained end-to-end with a"},"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":"1511.07571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-24T05:13:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c71d88ccd27cd5282e5dac16300c9f16287713510253e617b8b72615517156a","abstract_canon_sha256":"6fc3e30084afc00b80c965c6cde9e47aded34f5dd830e0ba3bcdcfaf2f8336b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:04.367646Z","signature_b64":"7T3F3sJQY3TvwWw8+EgMnPvI4q6wjQz+vl2zUov8ijZv6K15jOirQrTImA0m3G59gERDqpJzRhDHhGlePxhyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7ab4fcde70beeabe8eab18e7afc6fc705fc8d5375a2cd00c683dc341876e806","last_reissued_at":"2026-05-18T01:26:04.367142Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:04.367142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrej Karpathy, Justin Johnson, Li Fei-Fei","submitted_at":"2015-11-24T05:13:54Z","abstract_excerpt":"We introduce the dense captioning task, which requires a computer vision system to both localize and describe salient regions in images in natural language. The dense captioning task generalizes object detection when the descriptions consist of a single word, and Image Captioning when one predicted region covers the full image. To address the localization and description task jointly we propose a Fully Convolutional Localization Network (FCLN) architecture that processes an image with a single, efficient forward pass, requires no external regions proposals, and can be trained end-to-end with a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07571","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":"1511.07571","created_at":"2026-05-18T01:26:04.367222+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.07571v1","created_at":"2026-05-18T01:26:04.367222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07571","created_at":"2026-05-18T01:26:04.367222+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6VU7TPHBPXK","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6VU7TPHBPXKX2HK","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6VU7TPH","created_at":"2026-05-18T12:29:50.041715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02971","citing_title":"MedAutoCorrect: Image-Conditioned Autocorrection in Medical Reporting","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6VU7TPHBPXKX2HKWGHHV7DPY4","json":"https://pith.science/pith/Y6VU7TPHBPXKX2HKWGHHV7DPY4.json","graph_json":"https://pith.science/api/pith-number/Y6VU7TPHBPXKX2HKWGHHV7DPY4/graph.json","events_json":"https://pith.science/api/pith-number/Y6VU7TPHBPXKX2HKWGHHV7DPY4/events.json","paper":"https://pith.science/paper/Y6VU7TPH"},"agent_actions":{"view_html":"https://pith.science/pith/Y6VU7TPHBPXKX2HKWGHHV7DPY4","download_json":"https://pith.science/pith/Y6VU7TPHBPXKX2HKWGHHV7DPY4.json","view_paper":"https://pith.science/paper/Y6VU7TPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.07571&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6VU7TPHBPXKX2HKWGHHV7DPY4/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6VU7TPHBPXKX2HKWGHHV7DPY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6VU7TPHBPXKX2HKWGHHV7DPY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6VU7TPHBPXKX2HKWGHHV7DPY4/action/storage_attestation","attest_author":"https://pith.science/pith/Y6VU7TPHBPXKX2HKWGHHV7DPY4/action/author_attestation","sign_citation":"https://pith.science/pith/Y6VU7TPHBPXKX2HKWGHHV7DPY4/action/citation_signature","submit_replication":"https://pith.science/pith/Y6VU7TPHBPXKX2HKWGHHV7DPY4/action/replication_record"}},"created_at":"2026-05-18T01:26:04.367222+00:00","updated_at":"2026-05-18T01:26:04.367222+00:00"}