{"id":"W2509732107","doi":"10.1109/iscas.2016.7539152","title":"Approximation of feature pyramids in the DCT domain and its application to pedestrian detection","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Pedestrian detection; Computer science; Feature (linguistics); Artificial intelligence; Discrete cosine transform; Pyramid (geometry); Pattern recognition (psychology); Feature extraction; Histogram; Object detection; Domain (mathematical analysis); Bottleneck; Resampling; Computer vision; Image (mathematics); Mathematics; Pedestrian","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":[0.0002889094,0.00005277157,0.000059823,0.00007418744,0.0000289381,0.00002076266,0.0002265337,0.00003748929,7.40633e-7],"category_scores_gemma":[0.00005254503,0.00002778488,0.00001234014,0.0003765471,0.0000165115,0.0003873497,0.00004919329,0.00003868466,0.000002966128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001953881,"about_ca_system_score_gemma":0.000006674778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007295112,"about_ca_topic_score_gemma":0.00001799742,"domain_scores_codex":[0.9995148,0.00003676693,0.00009783491,0.0001599726,0.0001116235,0.00007903804],"domain_scores_gemma":[0.9996319,0.00005410681,0.0000440674,0.0002107978,0.00004000934,0.00001914656],"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":[0.000009656842,0.00001592739,0.00008722488,0.00001000895,8.746175e-7,3.03978e-7,0.0002855564,7.23241e-7,0.306471,0.03553106,0.00003470444,0.6575529],"study_design_scores_gemma":[0.0002233847,0.000164695,0.006040751,0.00002370209,0.000001325901,0.000008453586,0.00005079082,0.001419316,0.9334782,0.05575147,0.002745544,0.00009236087],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02622017,0.00003577899,0.9700539,0.002839667,0.00001080952,0.0003795842,5.137672e-7,0.00006267771,0.0003969729],"genre_scores_gemma":[0.9657662,0.00002630133,0.03396278,0.0001295707,0.00001429946,0.00004275173,2.399757e-7,0.000002305701,0.00005556422],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.939546,"threshold_uncertainty_score":0.1133035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01001794847998338,"score_gpt":0.2677295026376028,"score_spread":0.2577115541576194,"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."}}