{"id":"W2036880908","doi":"10.1007/s00371-014-0964-z","title":"Rotation invariance for dense features inside regions of interest","year":2014,"lang":"en","type":"article","venue":"The Visual Computer","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates - Technology Futures","keywords":"Scale invariance; Leverage (statistics); Invariant (physics); Computation; Computer science; Artificial intelligence; Image retrieval; Rotation (mathematics); Computer vision; Scale (ratio); Pattern recognition (psychology); Image (mathematics); Mathematics; Algorithm; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00008334297,0.00005954454,0.00007837368,0.00003196098,0.00003503871,0.00001896132,0.00007138414,0.00003117062,0.000001474801],"category_scores_gemma":[0.00001816502,0.00004455439,0.00003000601,0.00006363545,0.00001940426,0.00003065138,0.00001287591,0.00004585612,0.00000371831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008808128,"about_ca_system_score_gemma":0.000003328801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006442889,"about_ca_topic_score_gemma":0.0000249413,"domain_scores_codex":[0.9996907,0.00002707552,0.0001095765,0.00006030974,0.00003783231,0.00007452955],"domain_scores_gemma":[0.9996685,0.0001341886,0.00002537018,0.0001086449,0.00004638735,0.00001693102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002107018,0.00002103571,0.00006586259,0.00007543788,0.00002912718,2.76679e-7,0.0004542954,0.9136923,0.003858105,0.06482024,0.007333273,0.009628985],"study_design_scores_gemma":[0.0001861862,0.00007519196,0.001966166,0.00003277396,0.000009255365,0.000001828971,0.000007597178,0.989716,0.004624661,0.002387499,0.0009296719,0.00006316425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1773588,0.00001557019,0.8220595,0.0001297453,0.0002071752,0.0001086362,0.000001110937,0.0000451569,0.00007436102],"genre_scores_gemma":[0.9936536,0.000004013346,0.005938859,0.0001708173,0.000180616,0.000004935391,0.00001175748,0.00001412185,0.00002129097],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8162948,"threshold_uncertainty_score":0.1816875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03525864004156561,"score_gpt":0.2616815724582819,"score_spread":0.2264229324167163,"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."}}