{"id":"W2156406314","doi":"10.1109/tip.2015.2401516","title":"Integrated Foreground Segmentation and Boundary Matting for Live Videos","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Computer vision; Segmentation; Image segmentation; Discriminative model; Process (computing); Pixel; Video Graphics Array; Boundary (topology); Background subtraction; Image processing; Pattern recognition (psychology); Image (mathematics); 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":[0.0003547021,0.0001667485,0.0001372553,0.0001700204,0.0003694527,0.0007793124,0.0002274066,0.00005151662,0.000004468749],"category_scores_gemma":[0.00001655966,0.0001622316,0.00003796158,0.0002694502,0.0000874102,0.00243137,0.000003857638,0.0001539165,0.000009656336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001463697,"about_ca_system_score_gemma":0.0001725964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001817069,"about_ca_topic_score_gemma":0.00001004929,"domain_scores_codex":[0.9989154,0.00003674719,0.0002352855,0.0003621446,0.0002070052,0.0002434256],"domain_scores_gemma":[0.9992676,0.00006520516,0.0001082342,0.0001801186,0.0002942418,0.00008457192],"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":[0.00004515308,0.00010466,0.00000590507,0.0001399556,0.00001677088,0.000004722764,0.003554488,0.00005089369,0.04873091,0.0000403198,0.0004481855,0.946858],"study_design_scores_gemma":[0.0009030569,0.0003226626,0.000009992037,0.0002448694,0.00003451444,0.00004253664,0.001032865,0.2424516,0.75003,0.004022752,0.0005537778,0.0003512861],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003777932,0.0001294301,0.994267,0.0003494347,0.000198353,0.0004630636,0.0000060582,0.0005265732,0.0002820948],"genre_scores_gemma":[0.4073475,0.000006806014,0.5919749,0.000230202,0.00002259874,0.0001805793,0.000002855791,0.00001772936,0.0002168203],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9465067,"threshold_uncertainty_score":0.7514927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03039068224475167,"score_gpt":0.2981225484158856,"score_spread":0.267731866171134,"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."}}