{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001251187,0.00007413024,0.00005925644,0.00007232889,0.00008970904,0.00005428927,0.0001497022,0.00004064147,0.000007145946],"category_scores_gemma":[0.00008053915,0.0000633877,0.00004113625,0.000199047,0.00001048824,0.0004172653,0.00001434667,0.00006224073,0.000005850094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003291139,"about_ca_system_score_gemma":0.0000231861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001121809,"about_ca_topic_score_gemma":6.737317e-7,"domain_scores_codex":[0.9994423,0.00003138083,0.0000855104,0.0002275854,0.00008429621,0.0001289754],"domain_scores_gemma":[0.9995593,0.00004317974,0.00004506276,0.0002363901,0.00007544913,0.0000405926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001895039,0.0003905955,0.0008069311,0.00007913305,0.00001156962,0.000009733899,0.0003355756,0.001251806,0.4726032,0.1438601,0.01871094,0.3619215],"study_design_scores_gemma":[0.0009522214,0.00005720344,0.000161787,0.00002553641,0.000002438199,0.00001488203,0.00003798844,0.6362767,0.3388475,0.004840779,0.01859609,0.000186887],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000009129615,0.00001740799,0.9977379,0.0009333816,0.0001055812,0.0004589815,3.931784e-7,0.0001692334,0.0005679264],"genre_scores_gemma":[0.02764756,0.000001969349,0.9697378,0.001497161,0.000007818897,0.0001036748,0.000003014257,0.000006037193,0.0009949673],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6350248,"threshold_uncertainty_score":0.2584876,"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."}}