{"id":"W4386596814","doi":"10.1109/icip49359.2023.10222896","title":"Transpointflow: Learning Scene Flow from Point Clouds with Transformer","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China","keywords":"Computer science; Optical flow; Artificial intelligence; Point cloud; Transformer; Embedding; Computer vision; Feature (linguistics); Feature extraction; Pattern recognition (psychology); Feature matching; Matching (statistics); Image (mathematics); Mathematics; Voltage; Engineering","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":[0.0007095179,0.001635215,0.001128447,0.001796057,0.0004656585,0.001048679,0.002758236,0.001027711,0.003915876],"category_scores_gemma":[0.001652383,0.0008049104,0.001478993,0.00153202,0.0005511584,0.002084693,0.001449269,0.001765479,0.001713339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001054914,"about_ca_system_score_gemma":0.001467273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01509796,"about_ca_topic_score_gemma":0.01706178,"domain_scores_codex":[0.9997149,0.00002715909,0.00001232979,0.0001092905,0.00009572042,0.00004061245],"domain_scores_gemma":[0.9997087,0.00008152281,0.00002826851,0.00006186505,0.00008754508,0.00003198852],"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":[0.0002631728,0.0002905405,0.002156731,0.0001732335,0.0001724732,0.0001277806,0.00008599093,0.3016648,0.01323319,0.007981205,0.02173988,0.652111],"study_design_scores_gemma":[0.00001430102,0.00001713029,0.0001154729,0.000003505506,0.000005110726,0.00002098543,0.00000532548,0.9953348,0.001621502,0.002085613,0.0007707118,0.000005516955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008816807,0.000177023,0.9777017,0.00008865837,0.00007114659,0.0001181647,0.0005565813,0.01189716,0.0005728335],"genre_scores_gemma":[0.2165717,0.0004462824,0.771295,0.0002280947,0.000099485,0.0003197809,0.006610706,0.001248663,0.003180261],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01509796,"threshold_uncertainty_score":0.03002012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01046890397127671,"score_gpt":0.237218915388079,"score_spread":0.2267500114168023,"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."}}