{"id":"W1987435405","doi":"10.5244/c.14.77","title":"Recognizing Objects From Curvilinear Motion","year":2000,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Curvilinear coordinates; Artificial intelligence; Computer vision; Computer science; Basis (linear algebra); Optical flow; Motion (physics); Observer (physics); Object (grammar); Motion field; Set (abstract data type); Structure from motion; Motion estimation; Robot; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001737553,0.0005067919,0.0004794432,0.0008278704,0.0003355404,0.0005513837,0.0004686362,0.0004500304,0.001927578],"category_scores_gemma":[0.0005785021,0.0003400869,0.0004822313,0.0006755702,0.0004110388,0.001069284,0.001134004,0.000569918,0.0007482187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002287061,"about_ca_system_score_gemma":0.0003731469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003338439,"about_ca_topic_score_gemma":0.00512368,"domain_scores_codex":[0.9998623,0.00001434432,0.000006688509,0.00005448343,0.00003559438,0.00002653305],"domain_scores_gemma":[0.9998252,0.00003457254,0.00003164939,0.00005002566,0.00003332459,0.00002516103],"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":[0.000219505,0.00004649844,0.007161622,0.0001540118,0.00005883078,0.0003708096,0.0004997918,0.07654765,0.1677944,0.02423456,0.003231575,0.7196808],"study_design_scores_gemma":[0.00001725105,0.0001657312,0.02131986,0.00006748091,0.00003779017,0.0007511155,0.0003300472,0.8766809,0.04387986,0.03328609,0.02338153,0.00008239754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1108866,0.0004072877,0.8826321,0.0001315878,0.00004999738,0.00008745163,0.0003063283,0.001066789,0.004431823],"genre_scores_gemma":[0.4566591,0.0008796246,0.5332332,0.000116533,0.00004942071,0.00009531943,0.001804469,0.0001786149,0.006983579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003338439,"threshold_uncertainty_score":0.00663799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01294758730640022,"score_gpt":0.247660769962857,"score_spread":0.2347131826564568,"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."}}