{"id":"W2108957511","doi":"10.1109/icme.2011.6011898","title":"Semi-automatic synthetic depth map generation for video using random walks","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Random walk; Computer vision; Computer graphics (images); Artificial intelligence; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004344961,0.0008622372,0.0005068842,0.0007970185,0.0002731455,0.0005925162,0.0007958232,0.0006015587,0.002939405],"category_scores_gemma":[0.002091827,0.0004814016,0.0005568422,0.0004406649,0.0003150342,0.0006113231,0.000846027,0.0006904593,0.0008597714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003797877,"about_ca_system_score_gemma":0.0003635979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001768614,"about_ca_topic_score_gemma":0.003035372,"domain_scores_codex":[0.9996055,0.00009055622,0.00001502575,0.00007962847,0.000171489,0.00003791549],"domain_scores_gemma":[0.9992787,0.0003505094,0.0000612073,0.0001120039,0.0001437001,0.00005382741],"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":[0.0004490561,0.0001404498,0.0009053068,0.0002655721,0.00006984502,0.0002798467,0.0003094034,0.3228572,0.1375729,0.01249819,0.00635922,0.5182929],"study_design_scores_gemma":[0.00002524493,0.00003818646,0.0001726867,0.000009072743,0.000004250963,0.00009153591,0.00001647711,0.9771093,0.01699656,0.003189018,0.002333164,0.00001455232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00810906,0.00003861638,0.9898239,0.00002517378,0.000017277,0.0000466686,0.00007784597,0.001331539,0.0005298407],"genre_scores_gemma":[0.2190928,0.00008592776,0.7786217,0.00003530402,0.00002197347,0.0001696451,0.0004422937,0.0004911805,0.001039286],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002939405,"threshold_uncertainty_score":0.009833276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06965683246989471,"score_gpt":0.2972115507182502,"score_spread":0.2275547182483555,"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."}}