{"id":"W2111407473","doi":"10.1109/crv.2012.37","title":"Learning Categorical Shape from Captioned Images","year":2012,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Minimum bounding box; Object (grammar); Bounding overwatch; Computer vision; Boundary (topology); Active appearance model; Annotation; Set (abstract data type); Categorical variable; Pattern recognition (psychology); Image (mathematics); Class (philosophy); Cognitive neuroscience of visual object recognition; Mathematics; Machine learning","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":[0.0006956215,0.001496472,0.001173883,0.00177555,0.0003772364,0.001616022,0.002288016,0.002094124,0.002921145],"category_scores_gemma":[0.00423484,0.0007216728,0.00148631,0.001892337,0.000879075,0.002307112,0.001267843,0.001623731,0.002033214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107413,"about_ca_system_score_gemma":0.0005314859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003639519,"about_ca_topic_score_gemma":0.006271281,"domain_scores_codex":[0.9992803,0.0001205826,0.00002562492,0.0003590028,0.0001305043,0.00008396457],"domain_scores_gemma":[0.997785,0.000700591,0.0002313761,0.0006754843,0.0004484265,0.0001591247],"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":[0.0009612277,0.0002823774,0.007150943,0.0004200996,0.000196202,0.0008972496,0.0004254064,0.1668753,0.06584552,0.005988043,0.01391191,0.7370458],"study_design_scores_gemma":[0.00002325195,0.0001565787,0.002039141,0.0000299301,0.00002335291,0.0002524959,0.0001380045,0.9767618,0.01029486,0.007914358,0.002332893,0.00003341244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1692606,0.000571726,0.8138955,0.0003285884,0.000166861,0.0002482308,0.002416353,0.008968299,0.004143834],"genre_scores_gemma":[0.6534384,0.0004321153,0.3298505,0.0003918731,0.0001090277,0.0002137858,0.0119706,0.0004193981,0.003174281],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003639519,"threshold_uncertainty_score":0.009772182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01471669476561981,"score_gpt":0.2691605893443365,"score_spread":0.2544438945787166,"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."}}