{"id":"W4312731878","doi":"10.1109/cvpr52688.2022.00862","title":"HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":391,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Artificial intelligence; Invariant (physics); Transformer; Benchmark (surveying); Machine learning; Mathematics; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002368985,0.0002489679,0.0002609804,0.00021117,0.000392923,0.00005356629,0.0001523087,0.0001535875,0.0008161461],"category_scores_gemma":[0.000003049621,0.0002566099,0.000110077,0.0001254277,0.00005373205,0.0001419147,0.00003587027,0.0005646557,0.00005653159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008882249,"about_ca_system_score_gemma":0.00001843496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004783178,"about_ca_topic_score_gemma":0.00001030398,"domain_scores_codex":[0.9986094,0.00009982035,0.0003604228,0.000424426,0.0002123808,0.0002935399],"domain_scores_gemma":[0.9995385,0.00006894986,0.00005624701,0.0001754715,0.00005491725,0.0001058526],"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":[0.0001055066,0.0002123228,0.0002319689,0.00008662971,0.00005506606,0.000008868852,0.000406324,0.001178909,0.002933852,0.00014403,0.001921737,0.9927148],"study_design_scores_gemma":[0.00199442,0.001051277,0.006957222,0.00006378772,0.00003370154,0.00004482615,0.00007370546,0.9810554,0.002290244,0.0006375902,0.005419381,0.000378462],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.269761,0.00003170818,0.7260926,0.0006194627,0.001455754,0.000628192,0.0006451871,0.0005563928,0.0002096958],"genre_scores_gemma":[0.9967629,0.0001444133,0.00143779,0.0005225313,0.0001583193,0.0003284208,0.0005319137,0.00003828556,0.00007542416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9923363,"threshold_uncertainty_score":0.9999886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0446215628100976,"score_gpt":0.2561934175399021,"score_spread":0.2115718547298045,"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."}}