{"id":"W2137356988","doi":"10.1109/iccv.2013.319","title":"An Adaptive Descriptor Design for Object Recognition in the Wild","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Pipeline (software); Cognitive neuroscience of visual object recognition; Pixel; Object (grammar); Kernel (algebra); Pattern recognition (psychology); Invariant (physics); Set (abstract data type); Image processing","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":[0.0003755318,0.00007846386,0.00007266309,0.00005686427,0.00006392539,0.0001441147,0.0005151073,0.00003426185,0.00001516337],"category_scores_gemma":[0.00006709889,0.00004952929,0.00002872463,0.0002337201,0.00002041971,0.001689171,0.00002468787,0.00006994276,0.00003017188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002224052,"about_ca_system_score_gemma":0.00002169618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006643024,"about_ca_topic_score_gemma":0.000006713582,"domain_scores_codex":[0.9992968,0.0001047139,0.0001173363,0.0002092496,0.00009767099,0.0001741603],"domain_scores_gemma":[0.9993498,0.0002099419,0.00003354153,0.0002763597,0.0001017277,0.00002866576],"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":[0.00002904839,0.0001125615,0.00003140523,0.000004058291,0.000003950665,0.000002468565,0.0008321767,0.000008145606,0.00538716,0.008155675,0.008687149,0.9767462],"study_design_scores_gemma":[0.0005237776,0.002901428,0.001259813,0.00003880877,0.000005805026,0.00001571229,0.000673265,0.1264179,0.2638681,0.6019552,0.001924831,0.0004153226],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009596766,0.00002807931,0.9967754,0.0003015524,0.00003599263,0.0009310519,8.195607e-7,0.0001700462,0.0007973228],"genre_scores_gemma":[0.3416115,0.00001044646,0.6568587,0.001155661,0.00002726354,0.0002787213,0.000001429884,0.000004321473,0.00005195281],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9763309,"threshold_uncertainty_score":0.2019746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08230960480832816,"score_gpt":0.3019375382480531,"score_spread":0.2196279334397249,"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."}}