{"id":"W4405907339","doi":"10.1109/tpami.2024.3524377","title":"Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":237,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Object detection; Hypergraph; Computer vision; Computation; Object (grammar); Cognitive neuroscience of visual object recognition; Visualization; Pattern recognition (psychology); Mathematics; Algorithm","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":[0.0003631779,0.0002401838,0.0002534977,0.0009971124,0.0003082136,0.0004833101,0.0003011856,0.00008735601,0.00006976633],"category_scores_gemma":[0.000006955946,0.0002099394,0.0002411742,0.001478182,0.00005345367,0.0004547218,0.000006816528,0.000383425,0.0001046649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004412976,"about_ca_system_score_gemma":0.00002385468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001295876,"about_ca_topic_score_gemma":0.001496808,"domain_scores_codex":[0.9981511,0.0001722605,0.00037556,0.000753581,0.0003275126,0.0002199896],"domain_scores_gemma":[0.9991883,0.0001968786,0.0000757747,0.0003569806,0.00006587543,0.0001161645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007250908,0.00006137764,0.0001626709,0.00002580197,0.0002712152,0.000005309592,0.0003497669,0.01101374,0.001530053,0.0001271555,0.00001227942,0.9864334],"study_design_scores_gemma":[0.00005477849,0.0001685842,0.001234902,0.00003142848,0.0002989867,0.00002842352,0.00003174256,0.9604819,0.03599128,0.0003918493,0.001028708,0.000257358],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005021074,0.0003561012,0.9922403,0.001271968,0.0004625077,0.0001125207,0.00002487471,0.0003913666,0.0001192873],"genre_scores_gemma":[0.9973221,0.0003018247,0.001885439,0.0001905695,0.0000356034,0.00002377837,0.00002808959,0.00001545922,0.0001970657],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9923011,"threshold_uncertainty_score":0.8561078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01839729713418404,"score_gpt":0.286248052880697,"score_spread":0.267850755746513,"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."}}