{"id":"W2146307402","doi":"10.1109/tpami.2007.1126","title":"Flexible Spatial Configuration of Local Image Features","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; Pattern recognition (psychology); Image segmentation; Image processing; Image (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":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000301229,0.0001577313,0.0002555945,0.0004546984,0.000102001,0.00005778991,0.0002941807,0.00006241915,0.00006097114],"category_scores_gemma":[0.000004532858,0.000135347,0.0001765948,0.00087793,0.0001471575,0.0003806258,0.000004538455,0.0002011539,0.000007045226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002281269,"about_ca_system_score_gemma":0.00001389935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001074102,"about_ca_topic_score_gemma":0.000462407,"domain_scores_codex":[0.9988218,0.00003553089,0.0003670653,0.0003420748,0.0002482536,0.0001852868],"domain_scores_gemma":[0.9991748,0.000125442,0.0001240199,0.0003599644,0.000130874,0.00008486467],"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":[0.00002073885,0.00007741721,0.00003613303,0.00001021098,0.0001003197,0.000007085674,0.00009663301,0.0007923324,0.004203897,0.0002801444,0.000004746116,0.9943703],"study_design_scores_gemma":[0.00005163815,0.0001671489,0.001364867,0.00001326118,0.0001093367,0.000007259545,0.00003690301,0.004123793,0.9934276,0.000506054,0.00005325338,0.0001388417],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001427789,0.00009996327,0.9991592,0.0001155044,0.0000765592,0.00009749615,0.00001425632,0.000104913,0.0001893649],"genre_scores_gemma":[0.9906976,0.000217547,0.008698395,0.0002151811,0.00001311796,0.000003987696,0.000003458075,0.000006488004,0.0001441899],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9942315,"threshold_uncertainty_score":0.551929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01518564681937704,"score_gpt":0.3002712453400226,"score_spread":0.2850855985206455,"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."}}