{"id":"W4390893461","doi":"10.21203/rs.3.rs-3856948/v1","title":"GloFP-MSF: Monocular Scene Flow Estimation with Global Feature Perception","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Science Foundation of Heilongjiang Province; Fundamental Research Funds for the Central Universities; Government of Jiangsu Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China; Institute for Catastrophic Loss Reduction","keywords":"Monocular; Artificial intelligence; Computer science; Computer vision; Feature (linguistics); Optical flow; Motion (physics); Convolution (computer science); Motion estimation; Feature extraction; Image (mathematics); Pattern recognition (psychology); Artificial neural network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007330316,0.001486053,0.001226186,0.001211843,0.0005087177,0.001184346,0.00220703,0.001629296,0.01243868],"category_scores_gemma":[0.002811578,0.000730267,0.000671592,0.001154424,0.0004533896,0.002158512,0.001973151,0.001492267,0.006146621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004756629,"about_ca_system_score_gemma":0.001333979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01242056,"about_ca_topic_score_gemma":0.01195161,"domain_scores_codex":[0.9994757,0.00006681852,0.00001853011,0.0001300939,0.0002470646,0.00006170852],"domain_scores_gemma":[0.9994386,0.0001345691,0.00003166061,0.0001769643,0.00015685,0.00006139536],"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":[0.0003526979,0.000113669,0.000419376,0.0001240479,0.00007242059,0.00008647398,0.00006199638,0.0284845,0.02208495,0.00590452,0.0380377,0.9042575],"study_design_scores_gemma":[0.00007932571,0.00006304266,0.0004701641,0.00001765821,0.00001172826,0.0001062969,0.00001529134,0.9658015,0.01712886,0.005297211,0.01098598,0.00002288128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003246238,0.0001730591,0.9829392,0.00009632831,0.00009461319,0.00006174079,0.0006482753,0.01184995,0.0008904271],"genre_scores_gemma":[0.04480487,0.0002032264,0.9463868,0.0001149069,0.0001010132,0.0001842523,0.002961192,0.000997861,0.004245899],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01243868,"threshold_uncertainty_score":0.04161155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03626381843710688,"score_gpt":0.410113783702384,"score_spread":0.3738499652652771,"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."}}