{"id":"W2032473943","doi":"10.3115/1119212.1119216","title":"Towards a framework for learning structured shape models from text-annotated images","year":2003,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Image (mathematics); Set (abstract data type); Natural language processing; Translation (biology); Word (group theory); Structured prediction; Probabilistic logic; Segmentation; Image segmentation; Image translation; Training set; Computer vision; Pattern recognition (psychology); Mathematics","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":[0.003762233,0.002175398,0.002084683,0.003854501,0.001043437,0.003507173,0.006663484,0.004365664,0.003763708],"category_scores_gemma":[0.01021185,0.001886836,0.004239954,0.00445608,0.002276426,0.005073811,0.003503785,0.004277807,0.002491797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002857403,"about_ca_system_score_gemma":0.002132086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01002147,"about_ca_topic_score_gemma":0.01702751,"domain_scores_codex":[0.9978677,0.0006686712,0.0001307269,0.0008402931,0.0003869058,0.0001056402],"domain_scores_gemma":[0.9953756,0.002316795,0.0005361467,0.0009363908,0.0006193948,0.0002157065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003133309,0.0004353625,0.002861634,0.0007443052,0.0004325133,0.0005837017,0.0007984666,0.4049783,0.007690258,0.07365108,0.01846169,0.4890493],"study_design_scores_gemma":[0.00003580728,0.00007194269,0.0002242444,0.0000515943,0.00003436571,0.0001131473,0.00007305241,0.9302986,0.001320082,0.06396463,0.003784192,0.00002851246],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002170457,0.0002505279,0.9948732,0.0002521749,0.00002315668,0.00009674436,0.0004144656,0.001508269,0.0004109305],"genre_scores_gemma":[0.05645149,0.0005554719,0.934617,0.0004498199,0.0001367522,0.0007706843,0.004445304,0.0004264578,0.002147008],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01002147,"threshold_uncertainty_score":0.02073199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01857645544661559,"score_gpt":0.287877980988914,"score_spread":0.2693015255422984,"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."}}