{"id":"W2525668722","doi":"10.1016/j.patrec.2016.09.014","title":"Interactive deep learning method for segmenting moving objects","year":2016,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":336,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Ground truth; Artificial intelligence; Segmentation; Convolutional neural network; Computer vision; Margin (machine learning); Pixel; Market segmentation; Code (set theory); Deep learning; Pattern recognition (psychology); Machine learning; Set (abstract data type)","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":[0.001137127,0.0001735151,0.0001942601,0.0001655177,0.0001890759,0.0001655335,0.0003150306,0.00004867935,0.00003528008],"category_scores_gemma":[0.0003964092,0.0001390553,0.0001372785,0.0001581452,0.00001861888,0.0008024055,0.0001124663,0.0001482691,0.0001058059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007089201,"about_ca_system_score_gemma":0.000009831632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002075828,"about_ca_topic_score_gemma":0.00001327881,"domain_scores_codex":[0.9981902,0.0004420632,0.0002674207,0.0005165717,0.0001789623,0.0004048258],"domain_scores_gemma":[0.997598,0.001781462,0.0002244323,0.0002179539,0.0001105718,0.00006755839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000008195969,0.00001230674,0.003457889,0.00002152022,0.00003734826,0.00000763968,0.0006456478,0.00002164022,0.04907664,0.000005411373,0.00005509349,0.9466507],"study_design_scores_gemma":[0.01313121,0.0009202748,0.05882057,0.003179024,0.0001968384,0.0003924212,0.001155858,0.2382273,0.6534703,0.01498618,0.01063851,0.00488148],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03681544,0.00001312269,0.9589749,0.002920398,0.0006176006,0.0002145952,0.00000492315,0.0002506777,0.0001883592],"genre_scores_gemma":[0.5687392,0.000007787426,0.4267294,0.004110809,0.0002424011,0.0001050816,0.00001036049,0.00002485167,0.00003010069],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9417692,"threshold_uncertainty_score":0.5670511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02705768264026516,"score_gpt":0.3007710899321639,"score_spread":0.2737134072918987,"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."}}