{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004243244,0.0003068807,0.0003374388,0.0001971756,0.000157916,0.000296749,0.001399312,0.0002236722,0.00003309067],"category_scores_gemma":[0.0001407822,0.0002570375,0.00008808001,0.000276822,0.0000827414,0.0004656917,0.001870189,0.0006787761,0.00007447344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006990036,"about_ca_system_score_gemma":0.0001696244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002884282,"about_ca_topic_score_gemma":0.000309775,"domain_scores_codex":[0.9979433,0.0001401944,0.0004036775,0.0008402628,0.0003179571,0.0003545527],"domain_scores_gemma":[0.998193,0.0002932828,0.0001970462,0.001195092,0.00005953613,0.0000620307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001462614,0.00002306969,0.005675936,0.00005665001,0.0000143699,0.000003869693,0.002070409,0.003431979,0.00006396157,0.9869326,0.0001112448,0.001614388],"study_design_scores_gemma":[0.0002621368,0.00001664775,0.01034317,0.000500086,0.000006872469,0.000005010865,0.0002288809,0.07070447,0.0002023983,0.9157521,0.001361605,0.0006166389],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004818693,0.0002002274,0.9581795,0.007230123,0.0006044444,0.0003436718,0.000004882517,0.000674422,0.027944],"genre_scores_gemma":[0.8392356,0.00007596705,0.1597973,0.0001278443,0.000120268,0.0001572455,0.000005314136,0.00002306475,0.0004573595],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8344169,"threshold_uncertainty_score":0.9999882,"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."}}