{"id":"W2190067570","doi":"10.1109/cvpr.2016.501","title":"MovieQA: Understanding Stories in Movies through Question-Answering","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Karlsruhe House of Young Scientists; Deutsche Forschungsgemeinschaft","keywords":"Computer science; Question answering; Scripting language; Set (abstract data type); Benchmark (surveying); Comprehension; Semantics (computer science); Information retrieval; Natural language processing; Domain (mathematical analysis); CLIPS; Range (aeronautics); Artificial intelligence; Programming language","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":[0.002319202,0.0025823,0.001009445,0.003368802,0.001054551,0.002051045,0.002927799,0.003326702,0.01376144],"category_scores_gemma":[0.01469457,0.0004232551,0.001347935,0.001971847,0.0006332244,0.005275941,0.002485416,0.00250228,0.0078089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001425497,"about_ca_system_score_gemma":0.001074079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01344528,"about_ca_topic_score_gemma":0.02338779,"domain_scores_codex":[0.9972608,0.0009945291,0.0002461016,0.0007592622,0.0005538707,0.0001853722],"domain_scores_gemma":[0.9938545,0.003688115,0.0003463144,0.0009812003,0.0007144759,0.0004152909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002469207,0.003266492,0.02456999,0.006676126,0.0006880354,0.000862854,0.002601572,0.01236766,0.02130647,0.006857217,0.6673708,0.2509635],"study_design_scores_gemma":[0.001318696,0.002321339,0.08776189,0.0009820097,0.0004706862,0.002601613,0.004957375,0.2819079,0.03727916,0.02657209,0.5534953,0.0003319206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2614771,0.01152869,0.06955513,0.003919546,0.0009218288,0.003324224,0.5854383,0.03154106,0.03229421],"genre_scores_gemma":[0.1716415,0.0009620519,0.119571,0.0009484438,0.0002494958,0.001216641,0.6981582,0.0005798649,0.006672763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01376144,"threshold_uncertainty_score":0.0460366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06700293859533554,"score_gpt":0.3442383981747281,"score_spread":0.2772354595793926,"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."}}