{"id":"W4200200310","doi":"10.1109/iros51168.2021.9635875","title":"PLUMENet: Efficient 3D Object Detection from Stereo Images","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Point cloud; Computer vision; Lidar; Benchmark (surveying); Metric (unit); Object detection; Object (grammar); Feature (linguistics); Representation (politics); Exploit; Inference; Detector; Key (lock); Pattern recognition (psychology); Remote sensing; Engineering; 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":[0.0004897189,0.002529084,0.001752857,0.002852241,0.0004595921,0.001431373,0.005273409,0.001854587,0.004897505],"category_scores_gemma":[0.001569916,0.001265125,0.001444832,0.001862615,0.0005660901,0.002258652,0.002669811,0.001548134,0.003664285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001112416,"about_ca_system_score_gemma":0.001773458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0168927,"about_ca_topic_score_gemma":0.02931976,"domain_scores_codex":[0.9990653,0.00006576582,0.00002155888,0.0002048659,0.0005558535,0.0000867139],"domain_scores_gemma":[0.9995565,0.00008937826,0.00006129822,0.00009280689,0.0001569475,0.00004318997],"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":[0.0003382469,0.0003574953,0.001967051,0.0003108506,0.0002479412,0.0002659879,0.0000860049,0.08633278,0.03659103,0.004741019,0.04197501,0.8267866],"study_design_scores_gemma":[0.00004104373,0.00007209145,0.0005194456,0.00001490796,0.00001494692,0.0001446303,0.00002455917,0.9812837,0.00918253,0.004263863,0.004413134,0.00002507116],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01726795,0.0009842751,0.9356408,0.0002624159,0.0001538729,0.0003153381,0.002499716,0.04000962,0.002866016],"genre_scores_gemma":[0.1475309,0.0005680186,0.8361906,0.0004355164,0.0001223797,0.0003826711,0.009131808,0.001350285,0.004287845],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0168927,"threshold_uncertainty_score":0.03358877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04345949719033659,"score_gpt":0.2905566820600707,"score_spread":0.2470971848697341,"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."}}