{"id":"W1575833922","doi":"10.48550/arxiv.1505.02074","title":"Exploring Models and Data for Image Question Answering","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":390,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Image (mathematics); Question answering; Suite; Artificial intelligence; Segmentation; Image segmentation; Simple (philosophy); Object (grammar); Baseline (sea); Information retrieval; Pattern recognition (psychology); Machine learning; Data mining","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":[0.008460967,0.002298572,0.001697247,0.003373009,0.0009894086,0.00362408,0.004168534,0.004126429,0.004163468],"category_scores_gemma":[0.0391469,0.0008524997,0.002833024,0.002846571,0.001940202,0.01113566,0.004623545,0.005614033,0.002891325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003181083,"about_ca_system_score_gemma":0.001548955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008511794,"about_ca_topic_score_gemma":0.00939417,"domain_scores_codex":[0.9925256,0.004008802,0.0003584115,0.002107964,0.0007609351,0.0002383876],"domain_scores_gemma":[0.9751848,0.01753728,0.0009660153,0.004257829,0.001576787,0.0004772547],"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":[0.001633361,0.001847601,0.02381503,0.002594246,0.0006115886,0.0003894912,0.001420152,0.2878342,0.01179507,0.05764866,0.07647693,0.5339337],"study_design_scores_gemma":[0.00006453598,0.000151888,0.001298459,0.00009147044,0.0000460357,0.0001233129,0.0002552964,0.8974559,0.002781626,0.08701441,0.01067635,0.00004068692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09592718,0.008450113,0.8591858,0.009577334,0.0003897402,0.000541164,0.01478038,0.006618079,0.004530195],"genre_scores_gemma":[0.4621869,0.001745867,0.4788042,0.001963648,0.0004675657,0.0009868657,0.05053119,0.0004805771,0.002833211],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008511794,"threshold_uncertainty_score":0.0447464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4143372677061843,"score_gpt":0.2670283867265147,"score_spread":0.1473088809796696,"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."}}