{"id":"W2113854572","doi":"10.1109/icpr.2008.4761512","title":"Stereo matching using random walks","year":2008,"lang":"en","type":"article","venue":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Random walk; Matching (statistics); Pixel; Computer science; Artificial intelligence; Neighbourhood (mathematics); Laplace operator; Set (abstract data type); Algorithm; Mathematics; Computer vision; Pattern recognition (psychology); Statistics","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":[0.0009794907,0.0009012204,0.001438931,0.002534238,0.0008285902,0.001197953,0.001703601,0.001691798,0.00288412],"category_scores_gemma":[0.004069848,0.0008384986,0.001330673,0.001824449,0.0007405198,0.001952966,0.00190608,0.001125472,0.001381463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007631796,"about_ca_system_score_gemma":0.0009184285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003682205,"about_ca_topic_score_gemma":0.004287088,"domain_scores_codex":[0.9987565,0.0002809833,0.00006814955,0.0003288093,0.0004553482,0.0001103001],"domain_scores_gemma":[0.9987181,0.0005283863,0.0001635987,0.0002620041,0.0002470983,0.00008086414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002732311,0.0001521336,0.001395296,0.0001202064,0.0001456435,0.0001965656,0.0001552964,0.4589292,0.01932797,0.04137857,0.003476097,0.4744497],"study_design_scores_gemma":[0.00001823431,0.0000239457,0.0001437089,0.000006803937,0.000007185657,0.00006952714,0.000008869632,0.9809765,0.002606237,0.01508307,0.001042258,0.00001366669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006200696,0.00007094266,0.9925208,0.00003491729,0.00001582845,0.00003206333,0.00003197106,0.000510177,0.0005826268],"genre_scores_gemma":[0.2318107,0.0001469755,0.7641808,0.0001546629,0.00005312178,0.0001671702,0.0004113278,0.0002926659,0.00278255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003682205,"threshold_uncertainty_score":0.009648323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1238087922396459,"score_gpt":0.3241514014919863,"score_spread":0.2003426092523403,"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."}}