{"id":"W2102681574","doi":"10.1109/tpami.2004.30","title":"Gaussian MRF rotation-invariant features for image classification","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":153,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Invariant (physics); Gaussian; Computer science; Pattern recognition (psychology); Isotropy; Rotation (mathematics); Blob detection; Markov random field; Fourier transform; Algorithm; Computer vision; Mathematics; Image processing; Image segmentation; Image (mathematics); Edge detection; Mathematical analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.0002465561,0.0001984237,0.0002313282,0.0004482453,0.0003051384,0.0002630621,0.000414705,0.0001067265,0.00003254657],"category_scores_gemma":[0.00001017351,0.0001682074,0.0002433494,0.001005664,0.00007574278,0.0003802514,0.00000327583,0.0002389607,0.00002005097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006384629,"about_ca_system_score_gemma":0.00004194121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003948159,"about_ca_topic_score_gemma":0.0003132491,"domain_scores_codex":[0.9986152,0.00004634455,0.0003594189,0.0005364101,0.0002354346,0.0002071662],"domain_scores_gemma":[0.9989913,0.00009910369,0.0001459369,0.0004928295,0.0001616319,0.0001092525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000208925,0.000300968,0.00004168919,0.00003282721,0.0003063938,0.000004495931,0.0005133532,0.001251616,0.01173722,0.01067583,0.00001898425,0.9750957],"study_design_scores_gemma":[0.0001979953,0.0001924476,0.002675955,0.00002662443,0.0003193528,0.00001628425,0.00009686002,0.07804991,0.9115126,0.006427667,0.0001327389,0.0003515399],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001465187,0.0000536945,0.9953166,0.00375251,0.00009791221,0.0002897707,0.00004732452,0.0001864252,0.000109202],"genre_scores_gemma":[0.9651909,0.0002421284,0.03368194,0.0005023762,0.00002026096,0.0001214782,0.00001608859,0.00001092331,0.0002138456],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9747442,"threshold_uncertainty_score":0.6859299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02317500628798233,"score_gpt":0.2882098346277211,"score_spread":0.2650348283397387,"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."}}