{"id":"W2954369198","doi":"10.1109/access.2019.2924732","title":"Learning Robust Features for Planar Object Tracking","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; University of Alberta; National Science Foundation","keywords":"Computer science; Artificial intelligence; Robustness (evolution); Convolutional neural network; Computer vision; Deep learning; Motion blur; Feature extraction; Pattern recognition (psychology); Video tracking; Pixel; Eye tracking; Object (grammar); Image (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007664037,0.0001455049,0.0002216143,0.0001082042,0.0001606103,0.0006172544,0.001300028,0.00008292823,0.000009648119],"category_scores_gemma":[0.0001078968,0.0001304178,0.0001031759,0.0003071126,0.00001427944,0.001082818,0.000069232,0.0002331848,0.00003749826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002283209,"about_ca_system_score_gemma":0.00004743375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004392523,"about_ca_topic_score_gemma":0.00002939666,"domain_scores_codex":[0.9987013,0.000113183,0.0001702375,0.0004469285,0.0002079271,0.000360454],"domain_scores_gemma":[0.9987908,0.0005270477,0.0001126029,0.0004247157,0.00009009538,0.00005473426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001103302,0.0001260576,0.2452333,0.0003832784,0.0001748178,0.00005482951,0.002521553,0.09711085,0.01158306,0.01071262,0.008351033,0.6236382],"study_design_scores_gemma":[0.005183517,0.001170764,0.6436509,0.00050925,0.00005771427,0.0001948139,0.0002349566,0.109564,0.1519909,0.02567437,0.05881688,0.002951925],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1689855,0.0001767943,0.824287,0.0003269382,0.00218116,0.0003383121,0.0000023243,0.0003379809,0.003363919],"genre_scores_gemma":[0.962276,0.00001369239,0.03634771,0.0003667244,0.0002495279,0.00002209955,0.000003522365,0.00001934895,0.0007013817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7932904,"threshold_uncertainty_score":0.5952198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05293879379807757,"score_gpt":0.3374745261316309,"score_spread":0.2845357323335533,"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."}}