{"id":"W2148872184","doi":"10.1109/iccv.2007.4408832","title":"Detecting and Localizing 3D Object Classes using Viewpoint Invariant Reference Frames","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Artificial intelligence; Invariant (physics); Reference frame; Scale-invariant feature transform; Computer vision; Computer science; Pattern recognition (psychology); Object detection; Frame (networking); Cognitive neuroscience of visual object recognition; Frame of reference; Object (grammar); Mathematics; Feature extraction","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":[0.0007676256,0.0001566295,0.0001824734,0.0001344444,0.0002025576,0.0001968303,0.0003321232,0.00008463604,0.000008083676],"category_scores_gemma":[0.0002653371,0.0001302664,0.00002805149,0.0004386992,0.00005926283,0.0009250641,0.0003990699,0.0002384629,0.000004328431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005609945,"about_ca_system_score_gemma":0.00004467693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001290725,"about_ca_topic_score_gemma":0.00003564385,"domain_scores_codex":[0.9987072,0.00003863257,0.0002919523,0.0004035886,0.0001945149,0.0003640949],"domain_scores_gemma":[0.9990792,0.0002746543,0.0001052954,0.0003445304,0.00009553258,0.0001008373],"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":[0.0000152835,0.00003275492,0.001007299,0.00005935344,0.00001619215,0.0001181372,0.0004640877,0.00001805833,0.0873155,0.0423056,0.00003404336,0.8686137],"study_design_scores_gemma":[0.0002154809,0.0002095476,0.001301197,0.0002135026,0.00001091406,0.0002478455,0.0002546691,0.04672689,0.9260757,0.01946608,0.004736719,0.0005414439],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01226637,0.0005624652,0.9830949,0.00006741793,0.00005762386,0.0001203255,2.208565e-7,0.0004380232,0.003392605],"genre_scores_gemma":[0.4674702,0.00009073664,0.5318262,0.0005540033,0.00002690533,0.00000100265,1.287382e-7,0.000006945389,0.00002383379],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8680722,"threshold_uncertainty_score":0.5312111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05180517339674746,"score_gpt":0.3306590850671209,"score_spread":0.2788539116703734,"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."}}