{"id":"W1566289585","doi":"10.1109/iccv.2015.11","title":"Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books","year":2015,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":2068,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"","keywords":"Computer science; Reading (process); Context (archaeology); Semantics (computer science); Sentence; Embedding; Object (grammar); Artificial intelligence; Feeling; Natural language processing; Character (mathematics); Linguistics; Psychology; History","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":[0.0002834161,0.0007629422,0.0002569709,0.0005202683,0.0002783437,0.000907579,0.0007457805,0.0008417455,0.004448122],"category_scores_gemma":[0.002290468,0.0003593072,0.0006383325,0.0005375159,0.0004159119,0.002393796,0.0008487474,0.001176413,0.0009780509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004774238,"about_ca_system_score_gemma":0.0003918638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004727492,"about_ca_topic_score_gemma":0.008455875,"domain_scores_codex":[0.9998028,0.0000483525,0.000006689846,0.00009455799,0.00002992502,0.00001780736],"domain_scores_gemma":[0.9996352,0.000138054,0.00005739879,0.00007241093,0.0000654471,0.00003138803],"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":[0.0006945355,0.0003032994,0.01535984,0.0005684051,0.0002710068,0.0009039085,0.003014842,0.07789803,0.0741183,0.03498066,0.02653541,0.7653518],"study_design_scores_gemma":[0.00003874348,0.0001555213,0.0125357,0.00009767801,0.0001228415,0.0005327721,0.0009875154,0.8941216,0.02974631,0.03797665,0.02363104,0.00005356873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1977962,0.001326665,0.7792934,0.001353167,0.0001840743,0.0002011915,0.002121264,0.005970215,0.01175382],"genre_scores_gemma":[0.6557407,0.0007571069,0.3306255,0.0003248565,0.00009229362,0.00009447573,0.003929224,0.0003964749,0.00803926],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004727492,"threshold_uncertainty_score":0.01488042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0244207246769013,"score_gpt":0.3090277660838301,"score_spread":0.2846070414069288,"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."}}