{"id":"W4241072681","doi":"10.1109/icpr.2004.1334471","title":"A strongly coupled architecture for contextual object and scene identification","year":2004,"lang":"en","type":"article","venue":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Cognitive neuroscience of visual object recognition; Artificial intelligence; Intuition; Probabilistic logic; Architecture; Perception; Object detection; Context model; Human visual system model; Feed forward; Computer vision; Object (grammar); Pattern recognition (psychology); Cognitive science; Psychology; Engineering; Image (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":[],"consensus_categories":[],"category_scores_codex":[0.0003078937,0.0002343452,0.0002189415,0.0001968984,0.000157918,0.0002531351,0.0009687081,0.00009310065,0.00002125451],"category_scores_gemma":[0.0003026445,0.0001900092,0.0001136921,0.0002167146,0.0001458736,0.0006627127,0.000139427,0.0002207647,0.00001138163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001149186,"about_ca_system_score_gemma":0.00009554837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000398896,"about_ca_topic_score_gemma":0.00001375842,"domain_scores_codex":[0.9983124,0.000009830007,0.0004544426,0.0005028913,0.0004704907,0.0002500058],"domain_scores_gemma":[0.9978884,0.00005062869,0.0004673242,0.000176295,0.001342328,0.00007503549],"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":[0.0005680916,0.0008635077,0.003229098,0.0003807374,0.0003348727,0.000003661861,0.002044228,0.0001095955,0.1091198,0.07024761,0.002318709,0.8107801],"study_design_scores_gemma":[0.003645129,0.0008373121,0.006204994,0.001355059,0.00006139114,0.00009673777,0.0003353874,0.006719229,0.6149983,0.3643571,0.0006404336,0.0007488739],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08146327,0.0001264979,0.9103969,0.004863677,0.0004165704,0.001035718,0.0001528091,0.0001842819,0.001360331],"genre_scores_gemma":[0.9887158,0.00006493058,0.01020795,0.0005057087,0.0001209278,0.0001237283,0.00002325636,0.0000193708,0.0002183465],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9072525,"threshold_uncertainty_score":0.774835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03894633172846067,"score_gpt":0.2966568378642046,"score_spread":0.2577105061357439,"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."}}