{"id":"W2074685565","doi":"10.1007/s11263-006-8892-7","title":"Pre-Attentive and Attentive Detection of Humans in Wide-Field Scenes","year":2006,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Artificial intelligence; Probabilistic logic; Computer vision; Bayesian probability; Pattern recognition (psychology); Gaze; Saccadic masking; Prior probability; Eye movement","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":[0.0005855283,0.00008717198,0.0001821341,0.0003739825,0.00002468972,0.00009689499,0.0004575072,0.00004412311,0.000001999465],"category_scores_gemma":[0.00003540411,0.00007569761,0.00008308974,0.0001409249,0.00002875714,0.0005988475,0.0001479766,0.0001449582,8.812792e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003558807,"about_ca_system_score_gemma":0.00002622558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001007052,"about_ca_topic_score_gemma":0.00005025219,"domain_scores_codex":[0.99875,0.0001254506,0.0004762318,0.0001518242,0.0004014818,0.00009501723],"domain_scores_gemma":[0.9986947,0.0003344523,0.0003904167,0.000100329,0.0004544175,0.00002572048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002978962,0.0004360206,0.209478,0.00002470321,0.0001334913,0.0002329145,0.001105763,0.004186112,0.03309938,0.002729552,0.000291314,0.7479848],"study_design_scores_gemma":[0.0008639613,0.000480464,0.9472721,0.000268352,0.000004695244,0.0001170651,0.000009168114,0.02063394,0.02182039,0.008096785,0.0003327741,0.0001003431],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4684687,0.00009163314,0.5303398,0.0003199869,0.0006987079,0.00002662028,3.760117e-7,0.000005166591,0.0000490321],"genre_scores_gemma":[0.9605217,0.00003285285,0.039108,0.0001045098,0.000216903,4.939296e-7,4.653289e-7,0.000003944548,0.00001111129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7478845,"threshold_uncertainty_score":0.3086859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009060323129259432,"score_gpt":0.3020425760075991,"score_spread":0.2929822528783397,"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."}}