{"id":"W4405755237","doi":"10.1109/tcyb.2024.3515104","title":"RALACs: Action Recognition in Autonomous Vehicles Using Interaction Encoding and Optical Flow","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Optical flow; Encoding (memory); Action (physics); Computer science; Flow (mathematics); Action recognition; Human–computer interaction; Communication; Artificial intelligence; Psychology; Physics; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001863832,0.0001676777,0.0001354024,0.0004999884,0.0001452699,0.0003975646,0.00009942289,0.0001334587,0.00005706795],"category_scores_gemma":[0.00000544709,0.0001812798,0.00006975708,0.0003908928,0.0000411476,0.001038585,0.000003115732,0.0004517765,0.0001212473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002230731,"about_ca_system_score_gemma":0.00005231176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004951643,"about_ca_topic_score_gemma":0.0000933512,"domain_scores_codex":[0.9988043,0.00007238034,0.0002974706,0.0004220811,0.0001824921,0.0002212475],"domain_scores_gemma":[0.9995084,0.0001710839,0.00003928009,0.000154563,0.00004467206,0.00008201515],"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":[0.00002065626,0.0001284641,0.000004860669,0.00005397467,0.00002530594,0.0000331685,0.0007621782,0.008867279,0.01169788,0.0002483421,0.000029435,0.9781284],"study_design_scores_gemma":[0.0003020971,0.0001284445,0.0001299168,0.0003288445,0.00003797131,0.0001813076,0.0001423091,0.9018083,0.09378752,0.002320855,0.0005691783,0.0002632677],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3117835,0.00004754664,0.685751,0.0002101377,0.00133313,0.0001353878,0.000006211566,0.0002382691,0.0004948115],"genre_scores_gemma":[0.9862313,0.0002387534,0.01317611,0.00009256018,0.0001053389,0.00002168015,0.000004052608,0.000019096,0.0001111479],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9778652,"threshold_uncertainty_score":0.7392375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06092959981257284,"score_gpt":0.2972989119853907,"score_spread":0.2363693121728179,"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."}}