{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001668338,0.001345957,0.0007416733,0.0007929961,0.000384408,0.0005528469,0.001684254,0.001002776,0.002580198],"category_scores_gemma":[0.0119242,0.0003745726,0.0005446447,0.0006133643,0.0006231994,0.00143039,0.001208885,0.001816567,0.0008586011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006981306,"about_ca_system_score_gemma":0.0009619124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006099573,"about_ca_topic_score_gemma":0.006190024,"domain_scores_codex":[0.9990506,0.0001952108,0.00005813377,0.0003302453,0.0002446986,0.0001210924],"domain_scores_gemma":[0.9976028,0.0009092392,0.000236876,0.0005835144,0.0005204525,0.0001471737],"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":[0.0009271759,0.0007129686,0.007527635,0.0001983325,0.0001536828,0.0002159721,0.0001140927,0.2487753,0.05093436,0.001678151,0.009948554,0.6788138],"study_design_scores_gemma":[0.00002497034,0.0001910243,0.002224583,0.00001358743,0.00001563066,0.00008565928,0.00002267662,0.9780603,0.01702246,0.001141743,0.001177081,0.0000201956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1907096,0.001234679,0.7928769,0.0003338578,0.0004591506,0.0003373982,0.0007013631,0.01003841,0.003308668],"genre_scores_gemma":[0.8640206,0.0002317382,0.1295113,0.0003092906,0.00007689976,0.0003574168,0.001855341,0.0005492202,0.003088236],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006099573,"threshold_uncertainty_score":0.01212817,"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."}}