{"id":"W2109833684","doi":"10.1109/icip.2000.899818","title":"Incremental shape reconstruction using stereo image sequences","year":2000,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer vision; Computer science; Feature (linguistics); Matching (statistics); Iterative reconstruction; Representation (politics); Computer stereo vision; Stereopsis; Pattern recognition (psychology); Domain (mathematical analysis); Object (grammar); Correspondence problem; Feature extraction; Image (mathematics); Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007859436,0.00007038466,0.00006447591,0.00004701765,0.0001226245,0.0001477855,0.0002503462,0.00001419838,0.002331374],"category_scores_gemma":[0.000003754775,0.00006057867,0.00002596737,0.0001729027,0.00004547416,0.001737771,0.00005781042,0.00005550645,0.0001530977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000356389,"about_ca_system_score_gemma":0.0000203735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003536144,"about_ca_topic_score_gemma":0.000001723919,"domain_scores_codex":[0.9993511,0.0000230586,0.0001320556,0.0002201576,0.0001222077,0.000151385],"domain_scores_gemma":[0.9997178,0.00001056608,0.00002842412,0.0001738673,0.00002155508,0.00004781524],"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":[0.00000132464,0.000006197541,0.0002051418,0.000001164719,0.000001718251,0.000003746872,0.00005320944,0.00001460796,0.02459746,0.0005385233,0.00004142541,0.9745355],"study_design_scores_gemma":[0.0002118916,0.00002492587,0.0004831821,0.0000251426,0.000001695089,0.0002579381,0.0001198737,0.9751727,0.01968192,0.002296394,0.001552284,0.000172042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3755579,0.00003502097,0.579025,0.0003182416,0.0002385008,0.00007492454,6.081785e-7,0.0002309543,0.04451889],"genre_scores_gemma":[0.3148803,0.00001510916,0.684123,0.000531245,0.00003487231,7.998038e-7,2.991476e-7,0.000003484145,0.00041089],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9751581,"threshold_uncertainty_score":0.9985806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02585730675550598,"score_gpt":0.2950592126207097,"score_spread":0.2692019058652038,"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."}}