{"id":"W2470163766","doi":"10.1109/cvpr.2016.83","title":"Automatic Fence Segmentation in Videos of Dynamic Scenes","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Computer science; Artificial intelligence; Computer vision; Segmentation; Pixel; Conditional random field; Cut; Image segmentation; Coherence (philosophical gambling strategy); Graph; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00008014413,0.00003816701,0.00005787753,0.00007438062,0.00001165648,0.00001060886,0.0002069659,0.000007752656,0.00004445913],"category_scores_gemma":[0.00002821349,0.00002362569,0.0000120393,0.0001676326,0.00001844643,0.0005786613,0.00006191946,0.00001304813,0.00002992427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000271348,"about_ca_system_score_gemma":0.00001506107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007126697,"about_ca_topic_score_gemma":0.00000852109,"domain_scores_codex":[0.9995471,0.00001723006,0.0001356733,0.0001186363,0.00009768266,0.00008367764],"domain_scores_gemma":[0.9996967,0.00005821172,0.00004301766,0.0001643021,0.00001955016,0.00001819369],"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":[3.830373e-7,0.00001655829,0.001091788,0.00000583128,5.048851e-7,8.471044e-7,0.00009324216,0.000004583624,0.07296877,0.00242641,0.00001381558,0.9233773],"study_design_scores_gemma":[0.0004653205,0.00003816699,0.03756741,0.0001713202,5.90506e-7,0.00000370259,0.00005468657,0.8980752,0.05508776,0.008404336,0.00003290637,0.00009860158],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07296283,0.00001762052,0.9258034,0.000745613,0.00005650337,0.0000509014,1.476688e-7,0.0000548218,0.0003082235],"genre_scores_gemma":[0.7184913,0.000009944637,0.2812401,0.00009129346,0.000001066919,0.000002168575,5.637797e-8,0.000001324571,0.0001628222],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9232787,"threshold_uncertainty_score":0.09634275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008240783728107003,"score_gpt":0.2886367996042687,"score_spread":0.2803960158761618,"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."}}