{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:44VOJFLHI5355IDH2E2UUB7W67","short_pith_number":"pith:44VOJFLH","schema_version":"1.0","canonical_sha256":"e72ae495674777dea067d1354a07f6f7dd27ce7ed86880447c5f6a2c2fa518b5","source":{"kind":"arxiv","id":"2212.01803","version":1},"attestation_state":"computed","paper":{"title":"Controllable Image Captioning via Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahao Xie, Jihao Wu, Linlin Li, Mingbo Jia, Ning Wang","submitted_at":"2022-12-04T11:59:31Z","abstract_excerpt":"Despite the remarkable progress of image captioning, existing captioners typically lack the controllable capability to generate desired image captions, e.g., describing the image in a rough or detailed manner, in a factual or emotional view, etc. In this paper, we show that a unified model is qualified to perform well in diverse domains and freely switch among multiple styles. Such a controllable capability is achieved by embedding the prompt learning into the image captioning framework. To be specific, we design a set of prompts to fine-tune the pre-trained image captioner. These prompts allo"},"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":"2212.01803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-04T11:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"843c0fed15cdfcd2f17350064d1f06e4e8f777cf06c5073aaf9d48df1bf2f8d7","abstract_canon_sha256":"026316a666db5efacd317a1486779b3acb1a831bd3ef3d4a642d77559953bccc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:16.880554Z","signature_b64":"fJ0dI5YY5DxLU0IL8K/fGFsxn6eb2Ce0mFvTtT9sRNF4TYgz9EsfcQ/LdapKSPV1MSpdtgLnENk675rHam6ZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e72ae495674777dea067d1354a07f6f7dd27ce7ed86880447c5f6a2c2fa518b5","last_reissued_at":"2026-07-05T05:22:16.880219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:16.880219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Image Captioning via Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahao Xie, Jihao Wu, Linlin Li, Mingbo Jia, Ning Wang","submitted_at":"2022-12-04T11:59:31Z","abstract_excerpt":"Despite the remarkable progress of image captioning, existing captioners typically lack the controllable capability to generate desired image captions, e.g., describing the image in a rough or detailed manner, in a factual or emotional view, etc. In this paper, we show that a unified model is qualified to perform well in diverse domains and freely switch among multiple styles. Such a controllable capability is achieved by embedding the prompt learning into the image captioning framework. To be specific, we design a set of prompts to fine-tune the pre-trained image captioner. These prompts allo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01803","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.01803/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2212.01803","created_at":"2026-07-05T05:22:16.880268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.01803v1","created_at":"2026-07-05T05:22:16.880268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01803","created_at":"2026-07-05T05:22:16.880268+00:00"},{"alias_kind":"pith_short_12","alias_value":"44VOJFLHI535","created_at":"2026-07-05T05:22:16.880268+00:00"},{"alias_kind":"pith_short_16","alias_value":"44VOJFLHI5355IDH","created_at":"2026-07-05T05:22:16.880268+00:00"},{"alias_kind":"pith_short_8","alias_value":"44VOJFLH","created_at":"2026-07-05T05:22:16.880268+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/44VOJFLHI5355IDH2E2UUB7W67","json":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67.json","graph_json":"https://pith.science/api/pith-number/44VOJFLHI5355IDH2E2UUB7W67/graph.json","events_json":"https://pith.science/api/pith-number/44VOJFLHI5355IDH2E2UUB7W67/events.json","paper":"https://pith.science/paper/44VOJFLH"},"agent_actions":{"view_html":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67","download_json":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67.json","view_paper":"https://pith.science/paper/44VOJFLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.01803&json=true","fetch_graph":"https://pith.science/api/pith-number/44VOJFLHI5355IDH2E2UUB7W67/graph.json","fetch_events":"https://pith.science/api/pith-number/44VOJFLHI5355IDH2E2UUB7W67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67/action/storage_attestation","attest_author":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67/action/author_attestation","sign_citation":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67/action/citation_signature","submit_replication":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67/action/replication_record"}},"created_at":"2026-07-05T05:22:16.880268+00:00","updated_at":"2026-07-05T05:22:16.880268+00:00"}