{"id":"W3125886068","doi":"10.1109/cvpr46437.2021.00465","title":"Deep Multi-Task Learning for Joint Localization, Perception, and Prediction","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Computer science; Perception; Task (project management); Artificial intelligence; Reuse; Motion (physics); Autonomy; Architecture; Joint (building); Computation; Scale (ratio); Machine learning; Feature (linguistics); Motion planning; Robot; Algorithm; Engineering; Psychology","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":[0.0001464452,0.0002024029,0.0002097168,0.00008247178,0.0003332167,0.0002766794,0.0003067544,0.0001795184,0.00001482126],"category_scores_gemma":[0.00009024297,0.0002092576,0.00007632643,0.0002071319,0.00004519059,0.0002810572,0.0008798935,0.0003302935,0.000005260358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000790341,"about_ca_system_score_gemma":0.00005677275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001228535,"about_ca_topic_score_gemma":0.00003089805,"domain_scores_codex":[0.9983779,0.00006197442,0.0003428028,0.0008558548,0.0001546319,0.0002068524],"domain_scores_gemma":[0.9987695,0.00006944708,0.0001720309,0.0005333861,0.000359421,0.00009625508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002205484,0.00006408346,0.001040248,0.0001231169,0.00002723383,9.312164e-7,0.001343487,0.9325705,0.0008950441,0.003756428,0.0006497992,0.05952696],"study_design_scores_gemma":[0.0001937506,0.00002229587,0.003287206,0.00004004727,0.00001406377,0.00001005725,0.0001171666,0.9906446,0.00009735133,0.002352911,0.003027013,0.0001934951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006494903,0.0002433858,0.9968672,0.0006412864,0.0002973861,0.0007416838,0.000002537866,0.0004820607,0.00007492524],"genre_scores_gemma":[0.214503,0.0005557929,0.782607,0.0004069699,0.0002051286,0.0006281598,0.000294455,0.0000302902,0.0007691622],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2142602,"threshold_uncertainty_score":0.8533278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0309097520200706,"score_gpt":0.2755455068126552,"score_spread":0.2446357547925846,"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."}}