{"id":"W2116286708","doi":"10.1109/crv.2007.28","title":"Establishing Visual Correspondence from Multi-Resolution Graph Cuts for Stereo-Motion","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computation; Computer science; Graph; Pixel; Cut; Algorithm; Metric (unit); Artificial intelligence; Swap (finance); Computer vision; Smoothness; Mathematics; Theoretical computer science; Image (mathematics); Image segmentation","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":[0.0005407825,0.0001230321,0.0001108989,0.0001809454,0.0001961407,0.0002475358,0.0004647223,0.00005033259,0.00002001704],"category_scores_gemma":[0.0002114572,0.0001136482,0.00006361416,0.0003603164,0.00002847683,0.002138198,0.0001622834,0.0001061966,0.00003499172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005139718,"about_ca_system_score_gemma":0.00002163927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000887737,"about_ca_topic_score_gemma":0.00007609197,"domain_scores_codex":[0.9986925,0.00003024166,0.0002507605,0.0004304604,0.0002450799,0.0003510274],"domain_scores_gemma":[0.9990175,0.0003620532,0.00009593808,0.0002824896,0.0001275261,0.0001145422],"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":[0.00009031839,0.0001923223,0.002793752,0.000009318979,0.000009410635,0.0000126041,0.001046072,0.0004710374,0.026743,0.009712195,0.001670482,0.9572495],"study_design_scores_gemma":[0.0007634755,0.00006134665,0.01116992,0.00003347983,0.00000316196,0.000003891839,0.000172075,0.9714152,0.009709184,0.002670829,0.003789115,0.0002082662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008754658,0.00006887102,0.9892682,0.0001803776,0.0009153213,0.0002016757,0.000002792345,0.0002732436,0.0003349026],"genre_scores_gemma":[0.3024737,0.000004199584,0.6961219,0.0006295978,0.00008568351,0.000004999124,0.000009002301,0.000008552856,0.0006624324],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9709442,"threshold_uncertainty_score":0.4634438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03050785976653502,"score_gpt":0.3372370227214938,"score_spread":0.3067291629549588,"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."}}