{"id":"W3096393735","doi":"10.48550/arxiv.2011.00652","title":"Multi-View Adaptive Fusion Network for 3D Object Detection","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pointwise; Computer science; Benchmark (surveying); Fuse (electrical); Artificial intelligence; Lidar; Fusion; Weighting; Computer vision; Object detection; Object (grammar); Feature (linguistics); Key (lock); Point (geometry); Segmentation; Pattern recognition (psychology); Engineering; 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008947346,0.001445156,0.001001725,0.0008433685,0.0004870786,0.0006193467,0.002656898,0.001795345,0.002197062],"category_scores_gemma":[0.001616814,0.0006397003,0.001036094,0.0007612841,0.0005900265,0.00172366,0.001743706,0.001535307,0.0007417356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001164868,"about_ca_system_score_gemma":0.0007955707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008091736,"about_ca_topic_score_gemma":0.009501501,"domain_scores_codex":[0.9995674,0.0000477044,0.00001538509,0.000177866,0.0001113745,0.00008019946],"domain_scores_gemma":[0.9995634,0.0001288912,0.00004782045,0.00005629888,0.0001699319,0.00003365956],"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":[0.0004612168,0.0002788936,0.002834705,0.0001212801,0.0001921766,0.0002056952,0.0001330765,0.3787514,0.02307716,0.003395358,0.006277937,0.5842712],"study_design_scores_gemma":[0.000005050819,0.00004257439,0.0002989667,0.000005320877,0.00001762122,0.00002912525,0.000008935744,0.9942345,0.003403912,0.001563847,0.0003836858,0.000006452018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04582805,0.0008684812,0.9472097,0.0002804472,0.000112544,0.00007389295,0.0002297626,0.003401599,0.00199562],"genre_scores_gemma":[0.7342927,0.0004270207,0.2579329,0.0005065981,0.0001116517,0.0001633748,0.001028073,0.0001287172,0.005408817],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008091736,"threshold_uncertainty_score":0.01608932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1118443861595449,"score_gpt":0.2200124430115592,"score_spread":0.1081680568520144,"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."}}