{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CMPFM7R3PWWHRD7L3B6JORLZDI","short_pith_number":"pith:CMPFM7R3","schema_version":"1.0","canonical_sha256":"131e567e3b7dac788febd87c9745791a1767a53eea16740fdc00ab6dc15dac74","source":{"kind":"arxiv","id":"1811.10787","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Lin Ma, Wei Liu, Yang Feng","submitted_at":"2018-11-27T03:16:20Z","abstract_excerpt":"Deep neural networks have achieved great successes on the image captioning task. However, most of the existing models depend heavily on paired image-sentence datasets, which are very expensive to acquire. In this paper, we make the first attempt to train an image captioning model in an unsupervised manner. Instead of relying on manually labeled image-sentence pairs, our proposed model merely requires an image set, a sentence corpus, and an existing visual concept detector. The sentence corpus is used to teach the captioning model how to generate plausible sentences. Meanwhile, the knowledge in"},"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":"1811.10787","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T03:16:20Z","cross_cats_sorted":[],"title_canon_sha256":"330b5a86d0a38ef4dd2370d8a74f354eef94c815bb88a5fd3648dc7d68f886a2","abstract_canon_sha256":"3b69b347dbc2501520c138a84764794f0dcf1bd4e5af6afdba52bdc891936f39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:17.058939Z","signature_b64":"MfgUIjQgwPZaOH/iS9jNkBZdmtaaPx8b59SwUBHFJUISwmgycLIbO2IZ7cVLlNdPu7fTEEBWlXdVF8V2w5CxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"131e567e3b7dac788febd87c9745791a1767a53eea16740fdc00ab6dc15dac74","last_reissued_at":"2026-05-17T23:49:17.058283Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:17.058283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Lin Ma, Wei Liu, Yang Feng","submitted_at":"2018-11-27T03:16:20Z","abstract_excerpt":"Deep neural networks have achieved great successes on the image captioning task. However, most of the existing models depend heavily on paired image-sentence datasets, which are very expensive to acquire. In this paper, we make the first attempt to train an image captioning model in an unsupervised manner. Instead of relying on manually labeled image-sentence pairs, our proposed model merely requires an image set, a sentence corpus, and an existing visual concept detector. The sentence corpus is used to teach the captioning model how to generate plausible sentences. Meanwhile, the knowledge in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10787","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":"1811.10787","created_at":"2026-05-17T23:49:17.058383+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.10787v2","created_at":"2026-05-17T23:49:17.058383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10787","created_at":"2026-05-17T23:49:17.058383+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMPFM7R3PWWH","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMPFM7R3PWWHRD7L","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMPFM7R3","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.09317","citing_title":"Towards Unsupervised Image Captioning with Shared Multimodal Embeddings","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI","json":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI.json","graph_json":"https://pith.science/api/pith-number/CMPFM7R3PWWHRD7L3B6JORLZDI/graph.json","events_json":"https://pith.science/api/pith-number/CMPFM7R3PWWHRD7L3B6JORLZDI/events.json","paper":"https://pith.science/paper/CMPFM7R3"},"agent_actions":{"view_html":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI","download_json":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI.json","view_paper":"https://pith.science/paper/CMPFM7R3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.10787&json=true","fetch_graph":"https://pith.science/api/pith-number/CMPFM7R3PWWHRD7L3B6JORLZDI/graph.json","fetch_events":"https://pith.science/api/pith-number/CMPFM7R3PWWHRD7L3B6JORLZDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI/action/storage_attestation","attest_author":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI/action/author_attestation","sign_citation":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI/action/citation_signature","submit_replication":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI/action/replication_record"}},"created_at":"2026-05-17T23:49:17.058383+00:00","updated_at":"2026-05-17T23:49:17.058383+00:00"}