{"id":"W2163164795","doi":"10.1109/icpr.2008.4761007","title":"Structure from Motion: Combining features correspondences and optical flow","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":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Optical flow; Feature (linguistics); Probabilistic logic; Artificial intelligence; Computer vision; Computer science; Motion (physics); Motion estimation; Perspective (graphical); Flow (mathematics); Monte Carlo method; Structure from motion; Pattern recognition (psychology); Mathematics; Algorithm; Image (mathematics); Geometry; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003975071,0.001077196,0.0007400681,0.001131376,0.0007291611,0.0025856,0.002161857,0.0004457305,0.003299422],"category_scores_gemma":[0.0004638851,0.001087952,0.0002597781,0.0004731436,0.0004098352,0.004696051,0.0006266914,0.001533414,0.0006389376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003414708,"about_ca_system_score_gemma":0.0001418541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009367611,"about_ca_topic_score_gemma":0.00002579433,"domain_scores_codex":[0.9930967,0.00004013767,0.001209363,0.002378707,0.002406399,0.0008687103],"domain_scores_gemma":[0.9940206,0.0002225204,0.001023058,0.000253475,0.003932617,0.0005477501],"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":[0.0004647422,0.0005602962,0.009951789,0.00006704258,0.0003406513,0.00008551856,0.002141046,0.000004747696,0.009612005,0.01233725,0.001936873,0.962498],"study_design_scores_gemma":[0.01397789,0.002875559,0.1002624,0.008144438,0.0002819786,0.002854326,0.008864208,0.5756702,0.1006105,0.1769531,0.001831932,0.007673532],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7791743,0.00006706454,0.1072277,0.01641019,0.006298169,0.001390531,0.001824845,0.001282403,0.08632486],"genre_scores_gemma":[0.9805617,0.0008533383,0.01168914,0.00406398,0.001106217,0.000187981,0.001078238,0.00008766511,0.00037171],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9548245,"threshold_uncertainty_score":0.9991571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06885609883373368,"score_gpt":0.297112631449534,"score_spread":0.2282565326158003,"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."}}