{"id":"W2417002429","doi":"10.1109/wacv.2017.11","title":"Recurrent Fully Convolutional Networks for Video Segmentation","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Segmentation; Convolutional neural network; Artificial intelligence; Sliding window protocol; Frame (networking); Pattern recognition (psychology); Recurrent neural network; Image segmentation; Scale-space segmentation; Window (computing); Computer vision; Artificial neural network","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":[0.0003717187,0.0002446557,0.0002695262,0.00007997259,0.0002567844,0.0004489194,0.001414737,0.0001767004,0.00001212256],"category_scores_gemma":[0.0001316397,0.0002276312,0.0002500543,0.00004673193,0.00004795385,0.0005368808,0.001258068,0.0003301127,0.000008956192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001351419,"about_ca_system_score_gemma":0.0001816781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001464098,"about_ca_topic_score_gemma":0.000005537425,"domain_scores_codex":[0.9984334,0.00003357435,0.0003128005,0.0006749061,0.0002574203,0.0002879244],"domain_scores_gemma":[0.9981521,0.0001199959,0.0004072878,0.0009861386,0.0002517583,0.00008275169],"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":[0.00006380377,0.0001269332,0.0001716529,0.000172809,0.0001275948,0.00001339087,0.00008791441,0.001203913,0.0001841354,0.1038929,0.07111181,0.8228431],"study_design_scores_gemma":[0.0008136284,0.000387824,0.0006950519,0.000402784,0.00005586569,0.00001246634,0.000008510558,0.461934,0.01225515,0.4451552,0.07713431,0.001145182],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003467628,0.00106393,0.9936474,0.0005534774,0.00195323,0.0009826986,0.00001858979,0.0004718906,0.001274086],"genre_scores_gemma":[0.02865098,0.0003915794,0.9676531,0.0006126325,0.0005768337,0.0005706087,0.0001860877,0.00002364661,0.001334538],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.821698,"threshold_uncertainty_score":0.9282532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04481493431395485,"score_gpt":0.3500162957629044,"score_spread":0.3052013614489495,"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."}}