{"id":"W2096773956","doi":"10.1109/tpami.2004.1261075","title":"The use of force histograms for affine-invariant relative position description","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":115,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Affine transformation; Affine shape adaptation; Histogram; Position (finance); Artificial intelligence; Transformation (genetics); Invariant (physics); Computer vision; Affine coordinate system; Harris affine region detector; Mathematics; Pattern recognition (psychology); Computer science; Affine combination; Cognitive neuroscience of visual object recognition; Object (grammar); Affine space; Image (mathematics); Geometry","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":[0.0002112712,0.0001226008,0.0001648543,0.0002046407,0.0002988739,0.0001391727,0.0002448238,0.00005032574,0.000005309594],"category_scores_gemma":[0.000011047,0.00008698329,0.0002254647,0.0006997745,0.00008811592,0.0004443017,0.00000297904,0.0001175598,0.000002090006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006502559,"about_ca_system_score_gemma":0.00002044631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000523247,"about_ca_topic_score_gemma":0.0004387764,"domain_scores_codex":[0.9990374,0.00004916269,0.000332285,0.0002758189,0.0001709689,0.0001342991],"domain_scores_gemma":[0.9990888,0.0001950267,0.0001584694,0.0003403459,0.0001703264,0.000047079],"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":[0.00004049538,0.0001755453,0.00002743496,0.00001426206,0.0002979783,0.000001073299,0.0003962845,0.006345718,0.006449808,0.01043297,0.000004385786,0.975814],"study_design_scores_gemma":[0.0001470933,0.0003830153,0.0003754549,0.00003844683,0.0004190242,0.000008422327,0.00003443651,0.2023689,0.7846524,0.01110751,0.0002559373,0.0002094186],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003653118,0.00006457698,0.9980265,0.001132565,0.00007955579,0.0002291125,0.00002708234,0.00006509309,0.00001015849],"genre_scores_gemma":[0.9814251,0.0003814157,0.0176106,0.0001430566,0.000006815987,0.00004939538,0.000005833992,0.000005829041,0.000371934],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9810598,"threshold_uncertainty_score":0.3547075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04700270150546484,"score_gpt":0.273684099637006,"score_spread":0.2266813981315412,"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."}}