{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008427287,0.0007957345,0.002097961,0.0004325797,0.0006460798,0.0004362991,0.004868736,0.0002861104,0.00001384495],"category_scores_gemma":[0.00529073,0.0007241679,0.0006846554,0.002458938,0.00007845651,0.0001568771,0.002484916,0.002233828,0.0039974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001989538,"about_ca_system_score_gemma":0.0002034215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002204839,"about_ca_topic_score_gemma":0.0000074895,"domain_scores_codex":[0.9902976,0.005446617,0.001196107,0.001664183,0.0006402469,0.0007552553],"domain_scores_gemma":[0.9904139,0.00506504,0.001167485,0.003019392,0.0001355225,0.0001986776],"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":[9.431405e-8,0.00003721167,0.00001564476,0.01651076,0.00008384608,0.00001277342,0.00006745695,0.0009154077,2.738168e-8,0.001484805,0.0002949756,0.980577],"study_design_scores_gemma":[0.000209262,0.0001228636,0.0008468081,0.1054464,0.0003707503,0.0001209954,0.000007399732,0.202739,1.386088e-7,0.0004508384,0.6877186,0.00196696],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[8.06847e-7,0.7312114,0.2647992,0.0002717553,0.0002520596,0.0009254103,0.000002560606,0.001630609,0.0009062338],"genre_scores_gemma":[0.00003768383,0.9500902,0.04859335,0.00009699634,0.0002774606,0.0001697473,0.0002464404,0.0001612646,0.0003268627],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.97861,"threshold_uncertainty_score":0.999521,"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."}}