{"id":"W1995563672","doi":"10.1109/icinfa.2012.6246888","title":"An automatic method for detecting objects of interest in videos using surprise theory","year":2012,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Surprise; Salient; Novelty; Computer science; Artificial intelligence; Object (grammar); Computer vision; Pixel; Object detection; 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":[0.001940644,0.00007446621,0.0001291592,0.0001900151,0.00005195065,0.00003470862,0.0002294847,0.00004228837,0.00001478396],"category_scores_gemma":[0.0001642648,0.00006422939,0.00005380789,0.0003059796,0.00001152146,0.0007469998,0.00005468638,0.00005749659,0.000002693878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003555814,"about_ca_system_score_gemma":0.00001829892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005517873,"about_ca_topic_score_gemma":0.00008363547,"domain_scores_codex":[0.9990363,0.0002776291,0.0002590875,0.0001539135,0.00006376056,0.0002093127],"domain_scores_gemma":[0.9993318,0.0002363732,0.000101068,0.0002251415,0.00004545949,0.00006014502],"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":[0.0000228576,0.0004193886,0.004542846,0.0001629462,0.00001996375,8.986506e-7,0.009325619,0.0003490903,0.3130465,0.08172875,0.000004082422,0.590377],"study_design_scores_gemma":[0.0002326255,0.0001138891,0.003390265,0.00003410643,0.000005263592,0.00001166049,0.0007883772,0.8794596,0.1095638,0.006294352,0.000003370721,0.0001027168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4432417,0.000008517857,0.5563204,0.00000430346,0.0001785007,0.0001007888,1.343007e-7,0.00005796128,0.0000877908],"genre_scores_gemma":[0.7339895,1.678741e-7,0.2659229,0.00004156169,0.00002006572,0.000007069412,1.42094e-7,0.000004693415,0.00001389563],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8791105,"threshold_uncertainty_score":0.2619199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1259759776350849,"score_gpt":0.3937906255091976,"score_spread":0.2678146478741127,"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."}}