{"id":"W4386162736","doi":"10.1145/3617592","title":"Deep Learning Approaches on Image Captioning: A Review","year":2023,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":164,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Closed captioning; Computer science; Deep learning; Artificial intelligence; Modalities; Context (archaeology); Field (mathematics); Natural language processing; Image (mathematics); Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001743816,0.001417195,0.001138645,0.003227863,0.0003329866,0.001593487,0.001991772,0.001425617,0.005571042],"category_scores_gemma":[0.005127333,0.0006834535,0.0008163552,0.003915064,0.0006927071,0.003153774,0.001142674,0.001800055,0.003517564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009490824,"about_ca_system_score_gemma":0.001456081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002866802,"about_ca_topic_score_gemma":0.002974359,"domain_scores_codex":[0.9994963,0.00009883143,0.00005989321,0.0001049875,0.0002039859,0.00003595754],"domain_scores_gemma":[0.9970275,0.001933797,0.0001307086,0.0001030127,0.0007372604,0.00006778909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003461029,0.00005954921,0.0002498058,0.007723321,0.00007082496,0.0000519392,0.00006573812,0.001860375,0.0006170807,0.005278757,0.02591616,0.9580719],"study_design_scores_gemma":[0.00002750429,0.0002241119,0.001870727,0.01150377,0.0003022573,0.001166305,0.0001918895,0.008450468,0.003317778,0.01343766,0.9594078,0.00009971162],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0006307851,0.9811365,0.01234048,0.0009445751,0.0004298386,0.0000405159,0.0001098165,0.0001473083,0.004220328],"genre_scores_gemma":[0.004821733,0.9839358,0.008288825,0.0004754416,0.0004665304,0.0000446274,0.0002683106,0.00004559352,0.001653136],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.005571042,"threshold_uncertainty_score":0.018637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1770216083512234,"score_gpt":0.3854094199385489,"score_spread":0.2083878115873254,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}