{"id":"W1522233202","doi":"10.1007/978-3-642-37331-2_16","title":"Spatially Local Coding for Object Recognition","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Pooling; Artificial intelligence; Computer science; Pattern recognition (psychology); Coding (social sciences); Pyramid (geometry); Locality; Spatial analysis; Computer vision; Cognitive neuroscience of visual object recognition; Histogram; Feature (linguistics); Object (grammar); Image (mathematics); Geography; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006673548,0.0004796779,0.0004911943,0.0006267391,0.0002586519,0.00054132,0.002211925,0.0003264734,0.00003087909],"category_scores_gemma":[0.0001935988,0.0004425657,0.0001664317,0.0004132692,0.0005355342,0.00121991,0.0007767347,0.0005759115,0.00007511475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003188675,"about_ca_system_score_gemma":0.0003896902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001939981,"about_ca_topic_score_gemma":0.00002357975,"domain_scores_codex":[0.9968003,0.00002176704,0.0005048916,0.001387258,0.0006399413,0.0006458272],"domain_scores_gemma":[0.9974586,0.0006433377,0.0003062641,0.0009254705,0.0005199569,0.0001463393],"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":[0.000005294146,0.00001039128,0.000001222167,0.00003671615,0.000004573858,0.00001493256,0.0001063217,0.0005712588,0.0002459443,0.005503715,0.00005267553,0.9934469],"study_design_scores_gemma":[0.0002728698,0.000467393,0.000009730544,0.0005632475,0.000008719862,0.00004998729,1.039308e-7,0.3061046,0.04566758,0.6421932,0.003876888,0.000785691],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000005207989,0.0002371603,0.9946622,0.0003182132,0.0009758328,0.0009434462,0.000009731021,0.000367424,0.002480766],"genre_scores_gemma":[0.02164626,0.0001180945,0.9757761,0.001511026,0.000489414,0.0000503814,0.00001474702,0.00004335897,0.0003506393],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9926612,"threshold_uncertainty_score":0.9998026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02915410401670618,"score_gpt":0.2767206947243869,"score_spread":0.2475665907076808,"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."}}