{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002323333,0.00008759579,0.0001029644,0.0001456595,0.00009637197,0.0001720072,0.0002595331,0.00002621805,0.00003689014],"category_scores_gemma":[0.00006457086,0.00009023596,0.00003413477,0.0001459435,0.0000130304,0.002922346,0.0001087825,0.0001279027,0.000313364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005220806,"about_ca_system_score_gemma":0.00002270175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008173627,"about_ca_topic_score_gemma":0.00003067656,"domain_scores_codex":[0.9992515,0.00002466464,0.0002235916,0.0001866377,0.0001261705,0.0001873972],"domain_scores_gemma":[0.999371,0.0001925501,0.00008521441,0.0001996001,0.0001153006,0.00003635819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004521707,0.0001873413,0.02262269,0.0001281982,0.00003757378,0.000001450666,0.02205753,0.006608974,0.01356845,0.8394893,0.000324096,0.09492915],"study_design_scores_gemma":[0.003238777,0.0001641714,0.1813672,0.00008303983,0.000004755884,0.000004145526,0.001189142,0.8085543,0.001617264,0.001593346,0.001774729,0.0004091236],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5212542,0.000001545246,0.4729702,0.0001530508,0.00006017369,0.0004266104,0.000002411552,0.0001150214,0.005016801],"genre_scores_gemma":[0.9686899,8.71061e-7,0.03047101,0.000297985,0.00001815993,0.0003010672,0.00003074885,0.000005595514,0.0001846562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.837896,"threshold_uncertainty_score":0.4027765,"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."}}