{"id":"W4387490417","doi":"10.1109/tiv.2023.3323518","title":"MCHFormer: A Multi-Cross Hybrid Former of Point-Image for 3D Object Detection","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Point cloud; Computer science; Artificial intelligence; Computer vision; Object detection; Feature extraction; Feature (linguistics); Pattern recognition (psychology)","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":[0.000233724,0.0002199288,0.0002215444,0.000323178,0.0003889121,0.00007034566,0.0005418663,0.00006945514,0.00001405365],"category_scores_gemma":[0.00001472926,0.0002168821,0.0002569162,0.0008863456,0.0001198871,0.0006026568,0.00000748571,0.0002083613,0.0002073674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008340408,"about_ca_system_score_gemma":0.00003439815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002067653,"about_ca_topic_score_gemma":0.00006663836,"domain_scores_codex":[0.9982926,0.00003434356,0.000485877,0.0005038331,0.0002491425,0.000434184],"domain_scores_gemma":[0.9985436,0.000412115,0.0001557147,0.0005882895,0.000198162,0.000102188],"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":[0.0001666564,0.0004332755,0.00001539643,0.00009858307,0.00009116995,0.000003614423,0.0005815448,0.07692189,0.1081537,0.0005054972,0.0002249958,0.8128037],"study_design_scores_gemma":[0.0002909613,0.0001859423,0.00007827047,0.00002129251,0.00001354729,0.00001066364,0.00003882893,0.3346822,0.661847,0.001222505,0.001438738,0.0001700556],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03399683,0.00001933592,0.963851,0.0001807438,0.0005326429,0.0007779109,0.00007682729,0.000525173,0.00003955223],"genre_scores_gemma":[0.9171193,0.0001713482,0.08141598,0.00009981241,0.00004264382,0.000576253,0.000005621586,0.00003614805,0.0005329088],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8831224,"threshold_uncertainty_score":0.8844197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03565442813648844,"score_gpt":0.3113261137491017,"score_spread":0.2756716856126132,"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."}}