{"id":"W3104063540","doi":"","title":"An Adaptive Descriptor Design for Object Recognition in the Wild","year":2015,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; Cognitive neuroscience of visual object recognition; Kernel (algebra); Pipeline (software); Pixel; Set (abstract data type); Object (grammar); Pattern recognition (psychology); 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":[0.00165981,0.0002256414,0.0002329172,0.0001425699,0.0000612332,0.0002665855,0.001573188,0.000191116,0.000003232291],"category_scores_gemma":[0.0002019106,0.0001556719,0.00008311991,0.0002304929,0.00003713782,0.0007678609,0.0002962318,0.0003970785,0.000008425705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001200782,"about_ca_system_score_gemma":0.0002371512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006914937,"about_ca_topic_score_gemma":0.00001834502,"domain_scores_codex":[0.9983304,0.0003168696,0.0002592215,0.0005898304,0.0002444477,0.0002592487],"domain_scores_gemma":[0.9984059,0.0002548308,0.0001372119,0.0008228304,0.0003191768,0.00006009595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003166005,0.0003676219,0.00001770002,0.0000641779,0.00003208829,0.0000297092,0.003809706,0.000434552,0.0004929205,0.008442082,0.02928076,0.9567121],"study_design_scores_gemma":[0.0003332013,0.001436113,0.0000427038,0.0001440692,0.00001598191,0.00001134094,0.0002810197,0.09349147,0.02722338,0.8746713,0.001839942,0.0005095139],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000155039,0.0001791178,0.9959804,0.0002197306,0.0002114058,0.001758478,0.0000146322,0.000345022,0.001136204],"genre_scores_gemma":[0.08368498,0.00006364289,0.9146026,0.000819264,0.0001312978,0.0005854476,0.00002792758,0.00001617701,0.00006863219],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9562026,"threshold_uncertainty_score":0.6348117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1810566717527659,"score_gpt":0.3519386463420927,"score_spread":0.1708819745893269,"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."}}