{"id":"W4287333308","doi":"10.48550/arxiv.2102.01586","title":"U-LanD: Uncertainty-Driven Video Landmark Detection","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Landmark; Artificial intelligence; Margin (machine learning); Key (lock); Computer vision; Frame (networking); Overhead (engineering); Bayesian probability; Bayesian inference; Pattern recognition (psychology); Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002182317,0.001298797,0.001877036,0.001661965,0.000460233,0.001419744,0.003096361,0.001733715,0.002411495],"category_scores_gemma":[0.007507205,0.0007227368,0.001070404,0.001276285,0.001149298,0.002120386,0.002936919,0.002211322,0.001606318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008969064,"about_ca_system_score_gemma":0.001385339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007421449,"about_ca_topic_score_gemma":0.008869996,"domain_scores_codex":[0.9985707,0.0004184096,0.00005128835,0.0004869548,0.0003301182,0.0001424761],"domain_scores_gemma":[0.9981272,0.0009592634,0.0001927519,0.0003333388,0.0002617412,0.0001256824],"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":[0.0007395635,0.0002024915,0.003744987,0.000301377,0.000218603,0.0002773118,0.0002133314,0.2848223,0.01291053,0.01721153,0.01909837,0.6602596],"study_design_scores_gemma":[0.00002183284,0.00006497314,0.0002997568,0.00001409561,0.00001131353,0.00007792652,0.00002185392,0.9836427,0.00317648,0.01061119,0.002041765,0.00001615463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008652774,0.0006405051,0.9854835,0.0002403915,0.00006095266,0.00008271886,0.0003887218,0.003681452,0.0007689171],"genre_scores_gemma":[0.3552333,0.0006302748,0.6343637,0.0006341413,0.0002852896,0.0002697299,0.002929587,0.0007853364,0.004868703],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007421449,"threshold_uncertainty_score":0.01475656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05413472597586622,"score_gpt":0.1857636321285387,"score_spread":0.1316289061526725,"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."}}