{"id":"W2116957675","doi":"10.1109/tip.2005.863699","title":"Concurrent 3-D motion segmentation and 3-D interpretation of temporal sequences of monocular images","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Artificial intelligence; Computer vision; Motion field; Segmentation; Image segmentation; Scale-space segmentation; Mathematics; Motion estimation; Structure from motion; Segmentation-based object categorization; Computer science; Algorithm; 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":[0.0001147637,0.0001004023,0.0001345162,0.0001614752,0.00009872443,0.00007284069,0.0001132697,0.00002307637,0.000004211215],"category_scores_gemma":[0.000003288881,0.00009614896,0.00004075755,0.0002265311,0.0001206284,0.001471486,0.000002178572,0.00007959193,0.000001007569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002479294,"about_ca_system_score_gemma":0.00003175598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003546187,"about_ca_topic_score_gemma":0.000002227316,"domain_scores_codex":[0.9991568,0.00003932383,0.0003053051,0.000215115,0.0001850267,0.0000984387],"domain_scores_gemma":[0.9994741,0.00002988846,0.000213804,0.0001037536,0.000153979,0.00002448754],"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":[0.000004527888,0.00005996926,0.00003873137,0.00008599077,0.000002574459,6.632017e-7,0.0003178055,0.002528455,0.320687,0.00001833287,0.00000229198,0.6762537],"study_design_scores_gemma":[0.0002040407,0.00004195325,0.0001378768,0.0001133877,0.000008501314,0.00000482253,0.0001081936,0.3983616,0.6005417,0.0004102333,0.000001861851,0.00006583073],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02073406,0.0003239196,0.9785217,0.00008092425,0.0001021879,0.0001034472,0.000004893555,0.00005257548,0.00007628662],"genre_scores_gemma":[0.8272036,0.00001569149,0.1727317,0.00001443207,0.000005868299,0.000007141814,0.000001618698,0.000005229939,0.00001476718],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8064695,"threshold_uncertainty_score":0.3920841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01047985181827251,"score_gpt":0.2843979257652876,"score_spread":0.2739180739470151,"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."}}