{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000174046,0.00009429244,0.00009104692,0.00004863194,0.0001739461,0.00009480817,0.0004690284,0.0000450568,0.0004090288],"category_scores_gemma":[0.00008184688,0.00008259979,0.00003784467,0.00021632,0.00002025897,0.0004672286,0.0002079439,0.000249964,0.001953935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003136038,"about_ca_system_score_gemma":0.00001426318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001774756,"about_ca_topic_score_gemma":0.000002488978,"domain_scores_codex":[0.9991164,0.00008032979,0.0001290304,0.0002331247,0.0001693531,0.0002717507],"domain_scores_gemma":[0.9992529,0.0001735871,0.00004891634,0.0003418412,0.00003554997,0.0001472091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004414575,0.0003457857,0.37503,0.000005670443,0.00004234288,0.000003264567,0.003572278,0.001816616,0.02969544,0.3082829,0.00233066,0.2788707],"study_design_scores_gemma":[0.0001740637,0.00001600392,0.6024188,0.000001465313,0.000005682678,0.000006851235,0.00004313239,0.3882287,0.001138502,0.002223593,0.005528809,0.0002143498],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1999722,0.0000767326,0.7874886,0.002086094,0.0001267097,0.00007442571,5.458931e-7,0.0006371159,0.009537531],"genre_scores_gemma":[0.8882254,0.000002860545,0.1109512,0.0001498523,0.0001642976,0.0000226167,0.000008437068,0.000007874118,0.0004674018],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6882532,"threshold_uncertainty_score":0.9988232,"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."}}