{"id":"W2982151481","doi":"10.1109/iccv.2019.00184","title":"Exploring Overall Contextual Information for Image Captioning in Human-Like Cognitive Style","year":2019,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Closed captioning; Computer science; Sentence; Artificial intelligence; Encoder; ENCODE; Convolutional neural network; Salient; Natural language processing; Cognition; Speech recognition; Image (mathematics)","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":[0.0006186067,0.001476141,0.0004505219,0.0005544382,0.0002801453,0.0009775716,0.0008734397,0.0009784204,0.002571275],"category_scores_gemma":[0.002821204,0.0002760473,0.0009257433,0.0003940882,0.0004655897,0.00217729,0.0008195505,0.001177909,0.001105975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005335555,"about_ca_system_score_gemma":0.0004709299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002269763,"about_ca_topic_score_gemma":0.004192697,"domain_scores_codex":[0.9996666,0.0001032805,0.00001934208,0.0001293487,0.00004803299,0.00003347141],"domain_scores_gemma":[0.9992635,0.0003244265,0.00007678338,0.0001279555,0.0001601922,0.00004711487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006958622,0.0003269149,0.003065019,0.001259754,0.0002477209,0.0008686818,0.001217172,0.08708216,0.1427791,0.006138925,0.01975791,0.7365608],"study_design_scores_gemma":[0.00004159875,0.0004275785,0.003254063,0.00008853672,0.0001970733,0.000430706,0.0003157609,0.9114218,0.05773909,0.01101453,0.01499459,0.000074614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1882377,0.004798483,0.7812729,0.0009994151,0.0004741812,0.0004330793,0.002106952,0.01088428,0.01079307],"genre_scores_gemma":[0.6628211,0.001783414,0.3240928,0.0006508193,0.0002658548,0.0002490226,0.004138584,0.0004625919,0.005535804],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002571275,"threshold_uncertainty_score":0.008601785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04834636649097077,"score_gpt":0.298771803654511,"score_spread":0.2504254371635402,"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."}}