{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:6Z26G3SYNS6RX4ZBKHFAXF75A4","short_pith_number":"pith:6Z26G3SY","schema_version":"1.0","canonical_sha256":"f675e36e586cbd1bf32151ca0b97fd07238ebee03258530a5974572b9033e51e","source":{"kind":"arxiv","id":"1611.05321","version":3},"attestation_state":"computed","paper":{"title":"A Semi-supervised Framework for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aurelien Lucchi, Thomas Hofmann, Wenhu Chen","submitted_at":"2016-11-16T15:33:12Z","abstract_excerpt":"State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images, which is a much more abundant commodity. We here propose a novel way of using such textual data by artificially generating missing visual information. We evaluate this learning approach on a newly designed model that detects visual concepts present in an image and feed them to a reviewer-decoder architecture with an attention mechanism. Unlike previous appro"},"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":"1611.05321","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-16T15:33:12Z","cross_cats_sorted":[],"title_canon_sha256":"df7d24f7789c1aabf7bedd85e37aa16066d21a04a8d9928c53784e2b23767d8f","abstract_canon_sha256":"90002e8b80a175bd58f3a3326cdb3de886b05a42a5b559e81df94fbe0abd6889"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:47.869904Z","signature_b64":"WWuQhV9rAfJ8ZBMfn1hSZMz4OPOJ3jq+9W2ounM3Kw6gJgbFUYhA/n8eNK5J7xvRlZRHy73doi+asif5K7CWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f675e36e586cbd1bf32151ca0b97fd07238ebee03258530a5974572b9033e51e","last_reissued_at":"2026-05-18T00:41:47.869249Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:47.869249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Semi-supervised Framework for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aurelien Lucchi, Thomas Hofmann, Wenhu Chen","submitted_at":"2016-11-16T15:33:12Z","abstract_excerpt":"State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images, which is a much more abundant commodity. We here propose a novel way of using such textual data by artificially generating missing visual information. We evaluate this learning approach on a newly designed model that detects visual concepts present in an image and feed them to a reviewer-decoder architecture with an attention mechanism. Unlike previous appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05321","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":"1611.05321","created_at":"2026-05-18T00:41:47.869356+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.05321v3","created_at":"2026-05-18T00:41:47.869356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05321","created_at":"2026-05-18T00:41:47.869356+00:00"},{"alias_kind":"pith_short_12","alias_value":"6Z26G3SYNS6R","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"6Z26G3SYNS6RX4ZB","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"6Z26G3SY","created_at":"2026-05-18T12:30:04.600751+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/6Z26G3SYNS6RX4ZBKHFAXF75A4","json":"https://pith.science/pith/6Z26G3SYNS6RX4ZBKHFAXF75A4.json","graph_json":"https://pith.science/api/pith-number/6Z26G3SYNS6RX4ZBKHFAXF75A4/graph.json","events_json":"https://pith.science/api/pith-number/6Z26G3SYNS6RX4ZBKHFAXF75A4/events.json","paper":"https://pith.science/paper/6Z26G3SY"},"agent_actions":{"view_html":"https://pith.science/pith/6Z26G3SYNS6RX4ZBKHFAXF75A4","download_json":"https://pith.science/pith/6Z26G3SYNS6RX4ZBKHFAXF75A4.json","view_paper":"https://pith.science/paper/6Z26G3SY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.05321&json=true","fetch_graph":"https://pith.science/api/pith-number/6Z26G3SYNS6RX4ZBKHFAXF75A4/graph.json","fetch_events":"https://pith.science/api/pith-number/6Z26G3SYNS6RX4ZBKHFAXF75A4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6Z26G3SYNS6RX4ZBKHFAXF75A4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6Z26G3SYNS6RX4ZBKHFAXF75A4/action/storage_attestation","attest_author":"https://pith.science/pith/6Z26G3SYNS6RX4ZBKHFAXF75A4/action/author_attestation","sign_citation":"https://pith.science/pith/6Z26G3SYNS6RX4ZBKHFAXF75A4/action/citation_signature","submit_replication":"https://pith.science/pith/6Z26G3SYNS6RX4ZBKHFAXF75A4/action/replication_record"}},"created_at":"2026-05-18T00:41:47.869356+00:00","updated_at":"2026-05-18T00:41:47.869356+00:00"}