{"id":"W4386320522","doi":"10.1109/tip.2023.3309108","title":"Test-Time Adaptation for Optical Flow Estimation Using Motion Vectors","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; Huawei Technologies (Canada); McMaster University","funders":"Huawei Technologies","keywords":"Optical flow; Computer science; Artificial intelligence; Task (project management); Machine learning; Ground truth; Motion estimation; Test data; Adaptation (eye); Computer vision; Motion capture; Flow (mathematics); Motion (physics); Pattern recognition (psychology); Image (mathematics); Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002394422,0.0001570011,0.0001353854,0.0003247069,0.0005752357,0.0003277486,0.000199431,0.00005289428,0.000007987405],"category_scores_gemma":[0.00007124321,0.0001637452,0.00007709235,0.0008765075,0.00004453884,0.002179205,0.000002798986,0.0001430734,0.00009798242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001004953,"about_ca_system_score_gemma":0.00008350598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002010868,"about_ca_topic_score_gemma":4.785006e-7,"domain_scores_codex":[0.9987592,0.00001946631,0.0002589949,0.0003984835,0.000266884,0.0002970139],"domain_scores_gemma":[0.9992322,0.0002200705,0.00008776423,0.0001998874,0.0001802179,0.00007980126],"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":[0.000008417068,0.00004276936,2.678779e-7,0.0000390175,0.000002104331,0.000001584481,0.0002919271,0.2097109,0.05319737,0.00001111958,0.00001310948,0.7366814],"study_design_scores_gemma":[0.0003146089,0.00004860768,0.00002042517,0.00008846294,0.00001462455,0.00001051857,0.00005348885,0.8969228,0.1017049,0.0006454449,0.00001442216,0.0001617283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001011487,0.000007926625,0.9971876,0.000468092,0.0002853403,0.0002504629,0.000007664686,0.0007275585,0.00005393526],"genre_scores_gemma":[0.3251343,0.000002468442,0.6745892,0.00008297455,0.00002874601,0.00003197006,0.000004425583,0.00002074967,0.0001051868],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7365197,"threshold_uncertainty_score":0.6677334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03274438128194557,"score_gpt":0.3119314638443585,"score_spread":0.279187082562413,"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."}}