{"id":"W2102195578","doi":"10.1109/tpami.2011.202","title":"Spatiotemporal Stereo and Scene Flow via Stequel Matching","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Coherence (philosophical gambling strategy); Computer science; Computer vision; Optical flow; Matching (statistics); Correspondence problem; Ground truth; Motion estimation; Structure from motion; Pattern recognition (psychology); Image (mathematics); Mathematics","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":[0.0001823376,0.0002135694,0.0002737162,0.000419276,0.0002231887,0.0001247224,0.0003116086,0.00004225973,0.0001420926],"category_scores_gemma":[0.000001613681,0.0001845556,0.0001267804,0.000570567,0.0000657779,0.0005445527,0.00001245087,0.0002358612,0.00001950695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001742353,"about_ca_system_score_gemma":0.000009604547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001167849,"about_ca_topic_score_gemma":0.000553154,"domain_scores_codex":[0.9986566,0.00006500871,0.0003312553,0.0005227007,0.0002004366,0.0002239686],"domain_scores_gemma":[0.9992213,0.00005265481,0.00009712981,0.0004214789,0.00004801149,0.0001594634],"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":[0.000007300406,0.00007410181,0.0006317989,0.00001013844,0.0001220508,0.000009889543,0.001046084,0.0009595075,0.0003030761,0.00003253952,6.900385e-7,0.9968028],"study_design_scores_gemma":[0.0001145307,0.0001080361,0.002636834,0.00003264627,0.000157491,0.00002467725,0.0000873884,0.9236125,0.0711714,0.001722767,0.00002211833,0.0003095779],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003645611,0.0001230515,0.9956291,0.0001572873,0.0001475164,0.00008364103,0.00001091971,0.00008756742,0.0001152992],"genre_scores_gemma":[0.9289907,0.0002496277,0.07013276,0.0005022563,0.000009357971,0.000006611773,0.000001620446,0.00001026301,0.00009680505],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9964932,"threshold_uncertainty_score":0.752596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03099315085540459,"score_gpt":0.2756133055672482,"score_spread":0.2446201547118436,"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."}}