{"id":"W4313018251","doi":"10.1109/cvpr52688.2022.01668","title":"A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Lidar; Computer science; Object detection; Panopticon; Segmentation; Computer vision; Artificial intelligence; Object (grammar); Image segmentation; Remote sensing; Geography","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":[0.0004776739,0.001856366,0.001319434,0.00204232,0.000607827,0.001580872,0.002692144,0.00120446,0.002865827],"category_scores_gemma":[0.001033791,0.000880806,0.001640887,0.001213462,0.0004843386,0.001695258,0.003142304,0.001640395,0.001990515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005650279,"about_ca_system_score_gemma":0.001177844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01059749,"about_ca_topic_score_gemma":0.02208637,"domain_scores_codex":[0.9993259,0.00005746103,0.00001842287,0.0002557735,0.0002478824,0.00009457608],"domain_scores_gemma":[0.999625,0.00005147267,0.00003341092,0.0001186642,0.0001195717,0.00005201627],"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":[0.0003873621,0.0004121536,0.00392015,0.0002939979,0.0002826372,0.0003137618,0.0002855178,0.07040241,0.1003696,0.00693183,0.01866471,0.7977359],"study_design_scores_gemma":[0.00002712421,0.0000948931,0.00188965,0.00002587201,0.00004677022,0.0003234441,0.0001033436,0.9589236,0.02232393,0.006962187,0.009230289,0.00004905761],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008266912,0.0005301154,0.9817736,0.00008748477,0.00004593692,0.00009489094,0.0004839433,0.00745338,0.001263794],"genre_scores_gemma":[0.1887196,0.0005138013,0.8026949,0.0002810484,0.00009334512,0.0002316065,0.003705879,0.0009598206,0.002800007],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01059749,"threshold_uncertainty_score":0.02107161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04952368373759086,"score_gpt":0.2984373177444355,"score_spread":0.2489136340068447,"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."}}