{"id":"W1912960106","doi":"10.1109/icip.1999.821554","title":"A multi-frame, region-feature based technique for motion segmentation","year":2003,"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":"University of California, Santa Barbara","keywords":"Artificial intelligence; Computer science; Segmentation; Computer vision; Feature (linguistics); Frame (networking); Centroid; Cluster analysis; Trajectory; Image segmentation; Scale-space segmentation; Motion (physics); Pattern recognition (psychology)","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":[0.0005989299,0.001006506,0.001062086,0.002220362,0.0006078331,0.000674463,0.00152419,0.001537872,0.002976736],"category_scores_gemma":[0.001120387,0.0005910069,0.001132947,0.001645676,0.0004938085,0.001433097,0.0006372784,0.001130861,0.001805153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005739114,"about_ca_system_score_gemma":0.0006527092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002237751,"about_ca_topic_score_gemma":0.003571527,"domain_scores_codex":[0.9993815,0.00007584251,0.0000296307,0.0002000003,0.0002546268,0.00005836081],"domain_scores_gemma":[0.9994779,0.0001295337,0.00008486277,0.0001123794,0.0001653273,0.00002996541],"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":[0.000210201,0.00007522274,0.0004163964,0.0003130221,0.0001131126,0.0002919672,0.0001869292,0.01889517,0.278329,0.008700058,0.005046536,0.6874225],"study_design_scores_gemma":[0.00005322705,0.0004135543,0.003199731,0.00008530517,0.0001893148,0.002539202,0.00007994108,0.7398816,0.1856388,0.006879332,0.06087625,0.0001638072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001154944,0.0002156782,0.9975919,0.00002567543,0.00004215533,0.00003366244,0.00003497657,0.0006132129,0.0002878268],"genre_scores_gemma":[0.01851777,0.0002087766,0.980033,0.00003395816,0.00005777624,0.00006302099,0.0001266479,0.0001453146,0.0008137471],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002976736,"threshold_uncertainty_score":0.009958208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02451689149921166,"score_gpt":0.308869046476747,"score_spread":0.2843521549775353,"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."}}