{"id":"W3111344731","doi":"10.1109/smc42975.2020.9283183","title":"Quantifying the Impact of Complementary Visual and Textual Cues Under Image Captioning","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Closed captioning; Artificial intelligence; Feature (linguistics); Convolutional neural network; Encoder; Sentence; Natural language processing; Representation (politics); Sensory cue; Recurrent neural network; Pattern recognition (psychology); Image (mathematics); Speech recognition; Artificial neural network","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":[],"consensus_categories":[],"category_scores_codex":[0.0001291622,0.00007553952,0.00008965458,0.0000235723,0.0001529466,0.00009120854,0.0003232353,0.00001209531,0.00006819315],"category_scores_gemma":[0.00002247954,0.00004822096,0.00004157261,0.0001858318,0.00006419606,0.0001799232,0.0002726493,0.0001110284,0.00001566718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001269954,"about_ca_system_score_gemma":0.00002528985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004449304,"about_ca_topic_score_gemma":0.00003669156,"domain_scores_codex":[0.9993799,0.00005778599,0.0001447003,0.000186433,0.0001152923,0.0001159278],"domain_scores_gemma":[0.9995295,0.0001599771,0.00006328104,0.0001602066,0.00002839947,0.00005866692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000264743,0.0002089126,0.3827482,0.00005728094,0.000245741,0.000003410295,0.01319007,0.02327279,0.1964238,0.3345663,0.002826877,0.04643011],"study_design_scores_gemma":[0.0001443229,0.00007364972,0.3262116,0.000003200277,0.000003505872,0.000003450641,0.000412143,0.6723684,0.0004339188,0.0002666273,0.00001693807,0.00006227395],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5332736,0.00001911448,0.4615927,0.0044295,0.000005446627,0.00008983389,0.000002323949,0.0000699739,0.0005174557],"genre_scores_gemma":[0.9621356,0.000002123262,0.03746311,0.0003576641,0.00002534318,0.000004015624,0.000004263696,0.000004553473,0.000003292673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6490956,"threshold_uncertainty_score":0.6726047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06289478724702684,"score_gpt":0.3833081381672803,"score_spread":0.3204133509202535,"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."}}