{"id":"W2046103274","doi":"10.1109/bracis.2013.30","title":"Convolutional Sparse Feature Descriptor for Object Recognition in CIFAR-10","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Canadian Institute for Advanced Research","keywords":"Pattern recognition (psychology); Artificial intelligence; Computer science; Feature extraction; Neural coding; Feature (linguistics); Cognitive neuroscience of visual object recognition; Sparse approximation; Convolutional neural network; Benchmark (surveying); Feature learning; Feature vector; Representation (politics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001347906,0.0001014755,0.0001112492,0.0001008256,0.00005197656,0.00009182557,0.000277667,0.00007585086,0.000225091],"category_scores_gemma":[0.0001273404,0.00008727536,0.00005264597,0.0002562229,0.00002681412,0.001172572,0.0000692246,0.00009684158,0.000183251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005793589,"about_ca_system_score_gemma":0.00004281631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003603475,"about_ca_topic_score_gemma":0.00001150286,"domain_scores_codex":[0.9992184,0.00002251217,0.0001389036,0.0002720362,0.0001174163,0.0002306978],"domain_scores_gemma":[0.9994196,0.00008936947,0.00004311407,0.0001995395,0.0001955069,0.00005289399],"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":[0.00005311305,0.0002024445,0.0006249971,0.00004541812,0.00001600502,0.000007859792,0.0001712572,0.000003458398,0.02295732,0.02239385,0.327922,0.6256023],"study_design_scores_gemma":[0.002175144,0.0007788567,0.01369528,0.000144104,0.000009613053,0.00005065596,0.0001024659,0.03753525,0.3410726,0.4658219,0.1375602,0.001053936],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002077712,0.0001073413,0.9925954,0.001005562,0.0001197042,0.0005696391,0.00000560845,0.0002649084,0.003254065],"genre_scores_gemma":[0.1083111,0.00003600267,0.8827732,0.001251456,0.00009912221,0.00030561,0.00002824168,0.00001138487,0.007183936],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6245483,"threshold_uncertainty_score":0.3558986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03607463236671579,"score_gpt":0.2731042218637507,"score_spread":0.2370295894970349,"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."}}