{"id":"W1970862222","doi":"10.1109/tmm.2013.2283451","title":"Robust Semi-Automatic Depth Map Generation in Unconstrained Images and Video Sequences for 2D to Stereoscopic 3D Conversion","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; 2D to 3D conversion; Depth map; Stereoscopy; Rendering (computer graphics); Segmentation; Cut; Image segmentation; Image (mathematics)","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":[0.0001203645,0.0001541605,0.0001638691,0.0002403484,0.0001396656,0.0001427099,0.0001955262,0.00005127771,0.00006014053],"category_scores_gemma":[0.00001525883,0.0001415285,0.00003520784,0.0002142663,0.00005689184,0.0009091054,0.000003674325,0.0001165769,0.00007635345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006279571,"about_ca_system_score_gemma":0.00004273553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008562946,"about_ca_topic_score_gemma":0.00009023726,"domain_scores_codex":[0.99893,0.00004815454,0.0002468891,0.0003807792,0.0001530999,0.0002410814],"domain_scores_gemma":[0.9993203,0.000196674,0.00005076752,0.0002206431,0.00007390974,0.0001377319],"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":[0.00000782209,0.0001008137,0.0001175488,0.00006904863,0.00001330901,0.000003961137,0.001557379,0.02161974,0.06866248,0.000009077219,0.0007288093,0.90711],"study_design_scores_gemma":[0.0007889266,0.0001037308,0.0004176672,0.00006940365,0.000005795459,0.00000454338,0.0001478385,0.9494557,0.04870221,0.00005451683,0.00008367545,0.0001659948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03367507,0.00002930175,0.9637006,0.001209023,0.0005362115,0.0007099381,0.000008493457,0.0001066987,0.00002466105],"genre_scores_gemma":[0.5506642,0.00001145193,0.4486662,0.0003860891,0.00002200507,0.0001171861,0.000002586488,0.000007649898,0.0001225248],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9278359,"threshold_uncertainty_score":0.5771364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03018609404191342,"score_gpt":0.2728657174709004,"score_spread":0.242679623428987,"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."}}