{"id":"W2101670203","doi":"10.1109/crv.2007.67","title":"Using Feature Selection For Object Segmentation and Tracking","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Image segmentation; Relevance (law); Segmentation-based object categorization; Pattern recognition (psychology); Scale-space segmentation; Object (grammar); Computer vision; A priori and a posteriori; Video tracking; Feature (linguistics)","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":[0.0002190916,0.00005017553,0.00004696012,0.00005929398,0.0001017631,0.00007217403,0.00005883295,0.00003304431,8.165222e-7],"category_scores_gemma":[0.00002378029,0.00004436172,0.00001633918,0.0001883634,0.000007523566,0.0006833255,0.00001993826,0.00004118119,1.811583e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003230192,"about_ca_system_score_gemma":0.000009183632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006394731,"about_ca_topic_score_gemma":0.000008238943,"domain_scores_codex":[0.9996057,0.00000555964,0.0000657621,0.0001448045,0.00006132427,0.0001168795],"domain_scores_gemma":[0.9997783,0.00005063006,0.00003272312,0.00005454249,0.00006081258,0.00002301089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001337771,0.00001053633,0.001121484,0.00001483301,0.000004535583,8.741529e-7,0.0001854361,0.00000888158,0.3139309,0.006663607,0.0001719337,0.6778736],"study_design_scores_gemma":[0.0001353676,0.00007897856,0.001047895,0.000008237482,0.000003193408,0.00002634248,0.00003327038,0.02073352,0.9723472,0.004629835,0.0008739053,0.00008225187],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008043926,0.00006980937,0.991168,0.00005421582,0.00004227522,0.0001746232,1.81404e-7,0.0001831139,0.0002638208],"genre_scores_gemma":[0.2292675,0.000008128667,0.7704144,0.0001454269,0.00003740654,0.000001702216,5.589562e-7,0.000003364156,0.0001215758],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6777914,"threshold_uncertainty_score":0.1809019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04490353201592415,"score_gpt":0.3663971014955498,"score_spread":0.3214935694796256,"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."}}