{"id":"W1989066343","doi":"10.1109/tip.2014.2365140","title":"Local Symmetry Detection in Natural Images Using a Particle Filtering Approach","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Artificial intelligence; Symmetry (geometry); Reflection symmetry; Computer vision; Homogeneous space; Segmentation; Local symmetry; Tracking (education); Image segmentation; Computer science; Particle filter; Ribbon; Object detection; Algorithm; Mathematics; Pattern recognition (psychology); Geometry; Physics","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":[0.0003125688,0.0002038011,0.0001983428,0.0002433699,0.0002911533,0.0002991589,0.0003380102,0.00006951802,0.00000219952],"category_scores_gemma":[0.00002010463,0.0002010076,0.0000738012,0.0009694429,0.0001042957,0.002349715,0.000007578981,0.0004371807,0.000006152541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001484355,"about_ca_system_score_gemma":0.00003565757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002888156,"about_ca_topic_score_gemma":0.000005667545,"domain_scores_codex":[0.9984994,0.00008836455,0.0002930615,0.0004883349,0.0002397595,0.0003910909],"domain_scores_gemma":[0.9993822,0.0000619116,0.0000864317,0.0003078559,0.00008879178,0.0000728306],"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":[0.00001993894,0.00009434841,0.000003280053,0.00006196748,0.000003206279,0.000005148473,0.0001553379,0.00161468,0.232313,0.0000168164,7.94592e-7,0.7657115],"study_design_scores_gemma":[0.0001780571,0.00003858148,0.00002961787,0.00005640735,0.000004525693,0.00003321615,0.00003405149,0.4660736,0.533039,0.0003617263,0.00001152597,0.0001396307],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01039163,0.0001275472,0.988529,0.00003704389,0.0001411738,0.0001502561,8.087204e-7,0.000445539,0.0001770676],"genre_scores_gemma":[0.7086285,0.000006648255,0.2912031,0.00008242449,0.00002071469,0.00001979842,1.732446e-7,0.00001689791,0.00002176935],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7655718,"threshold_uncertainty_score":0.819685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0173380745742751,"score_gpt":0.2804942661278961,"score_spread":0.263156191553621,"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."}}