{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:444CBFPYTUFUBE4W2DSBE2H5HI","short_pith_number":"pith:444CBFPY","schema_version":"1.0","canonical_sha256":"e7382095f89d0b409396d0e41268fd3a2da97df11234a93feef54609789396c6","source":{"kind":"arxiv","id":"1810.04020","version":2},"attestation_state":"computed","paper":{"title":"A Comprehensive Survey of Deep Learning for Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ferdous Sohel, Hamid Laga, Md. Zakir Hossain, Mohd Fairuz Shiratuddin","submitted_at":"2018-10-06T16:31:52Z","abstract_excerpt":"Generating a description of an image is called image captioning. Image captioning requires to recognize the important objects, their attributes and their relationships in an image. It also needs to generate syntactically and semantically correct sentences. Deep learning-based techniques are capable of handling the complexities and challenges of image captioning. In this survey paper, we aim to present a comprehensive review of existing deep learning-based image captioning techniques. We discuss the foundation of the techniques to analyze their performances, strengths and limitations. We also d"},"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":"1810.04020","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-10-06T16:31:52Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"a7d115eaef9acacaafd1395b9752d1693fa719a0adfe2b393148c1451a942c34","abstract_canon_sha256":"0463aad7df7cd46bd0193d20d29282984be3dac987d570a3dddc19c0ffc1f72d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:23.941074Z","signature_b64":"XbVd+csQzZQS4b6Z9iNo9+4xpll4Hm8V9h0o2HZ2wkks0rVrpi1Bq9U+s4ter6celF1L8Jtkfr/ABGsiU2BjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7382095f89d0b409396d0e41268fd3a2da97df11234a93feef54609789396c6","last_reissued_at":"2026-05-18T00:03:23.940567Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:23.940567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Survey of Deep Learning for Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ferdous Sohel, Hamid Laga, Md. Zakir Hossain, Mohd Fairuz Shiratuddin","submitted_at":"2018-10-06T16:31:52Z","abstract_excerpt":"Generating a description of an image is called image captioning. Image captioning requires to recognize the important objects, their attributes and their relationships in an image. It also needs to generate syntactically and semantically correct sentences. Deep learning-based techniques are capable of handling the complexities and challenges of image captioning. In this survey paper, we aim to present a comprehensive review of existing deep learning-based image captioning techniques. We discuss the foundation of the techniques to analyze their performances, strengths and limitations. We also d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04020","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":"1810.04020","created_at":"2026-05-18T00:03:23.940657+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.04020v2","created_at":"2026-05-18T00:03:23.940657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04020","created_at":"2026-05-18T00:03:23.940657+00:00"},{"alias_kind":"pith_short_12","alias_value":"444CBFPYTUFU","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"444CBFPYTUFUBE4W","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"444CBFPY","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07480","citing_title":"Remaining Useful Lifetime Prediction via Deep Domain Adaptation","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/444CBFPYTUFUBE4W2DSBE2H5HI","json":"https://pith.science/pith/444CBFPYTUFUBE4W2DSBE2H5HI.json","graph_json":"https://pith.science/api/pith-number/444CBFPYTUFUBE4W2DSBE2H5HI/graph.json","events_json":"https://pith.science/api/pith-number/444CBFPYTUFUBE4W2DSBE2H5HI/events.json","paper":"https://pith.science/paper/444CBFPY"},"agent_actions":{"view_html":"https://pith.science/pith/444CBFPYTUFUBE4W2DSBE2H5HI","download_json":"https://pith.science/pith/444CBFPYTUFUBE4W2DSBE2H5HI.json","view_paper":"https://pith.science/paper/444CBFPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.04020&json=true","fetch_graph":"https://pith.science/api/pith-number/444CBFPYTUFUBE4W2DSBE2H5HI/graph.json","fetch_events":"https://pith.science/api/pith-number/444CBFPYTUFUBE4W2DSBE2H5HI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/444CBFPYTUFUBE4W2DSBE2H5HI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/444CBFPYTUFUBE4W2DSBE2H5HI/action/storage_attestation","attest_author":"https://pith.science/pith/444CBFPYTUFUBE4W2DSBE2H5HI/action/author_attestation","sign_citation":"https://pith.science/pith/444CBFPYTUFUBE4W2DSBE2H5HI/action/citation_signature","submit_replication":"https://pith.science/pith/444CBFPYTUFUBE4W2DSBE2H5HI/action/replication_record"}},"created_at":"2026-05-18T00:03:23.940657+00:00","updated_at":"2026-05-18T00:03:23.940657+00:00"}