{"id":"W3004414032","doi":"10.1109/iros40897.2019.8968242","title":"Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Computer science; Orientation (vector space); Computer vision; Artificial intelligence; Point cloud; Pose; Benchmark (surveying); Process (computing); Object detection; Pedestrian; Object (grammar); Point (geometry); View synthesis; Tracking (education); Task (project management); Video tracking; Segmentation; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001248332,0.0001210154,0.0001168602,0.00006792945,0.0001624903,0.00009081298,0.000238387,0.000040681,0.000006922237],"category_scores_gemma":[0.00007108993,0.0001003995,0.00003397162,0.000389235,0.00001534251,0.0008568741,0.00004054621,0.0000601034,0.00005939697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007397067,"about_ca_system_score_gemma":0.00004042859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002619608,"about_ca_topic_score_gemma":0.00007280192,"domain_scores_codex":[0.9990487,0.00002659483,0.0001804066,0.0004112998,0.0001427637,0.0001902087],"domain_scores_gemma":[0.9989921,0.0003448325,0.0001420478,0.0003815531,0.00009388856,0.00004552231],"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":[0.00002044137,0.00003633815,0.0000901922,0.00002281069,0.000007478503,2.138868e-7,0.00009619809,0.032599,0.01073759,0.006004244,0.000006452874,0.9503791],"study_design_scores_gemma":[0.0003717057,0.0002386117,0.00041014,0.00001583085,0.00001304145,0.000007864535,0.00003388518,0.9702703,0.02816717,0.0001799085,0.0001370091,0.0001545725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02386592,0.000006526908,0.9744706,0.0001101918,0.0001368217,0.001026328,0.000001824905,0.0002930235,0.00008878287],"genre_scores_gemma":[0.5671549,0.00000237471,0.4322862,0.00005100405,0.00002132778,0.0002970798,0.000003131798,0.000009774412,0.0001741625],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9502245,"threshold_uncertainty_score":0.4094175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01494533313518306,"score_gpt":0.261779489040155,"score_spread":0.246834155904972,"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."}}