{"id":"W4285819379","doi":"10.1109/tits.2022.3177367","title":"ST CrossingPose: A Spatial-Temporal Graph Convolutional Network for Skeleton-Based Pedestrian Crossing Intention Prediction","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"European Commission; Royal Academy of Engineering; York University","keywords":"Computer science; Pedestrian; Inference; Graph; Artificial intelligence; Convolutional neural network; Context (archaeology); Spatial contextual awareness; Limiting; Data mining; Pattern recognition (psychology); Machine learning; Theoretical computer science; Engineering; Geography; Transport engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004838254,0.0003104466,0.0003264388,0.0003345825,0.001708194,0.0001081642,0.000189486,0.0002186349,0.000180751],"category_scores_gemma":[0.000002091875,0.0003759546,0.0003228096,0.0005138845,0.000171752,0.0001670115,3.729604e-7,0.0005437149,0.00001006963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004343451,"about_ca_system_score_gemma":0.0001661937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004173286,"about_ca_topic_score_gemma":0.0006846787,"domain_scores_codex":[0.9977736,0.0000683434,0.0009263662,0.0004132678,0.0003840891,0.0004343535],"domain_scores_gemma":[0.9992079,0.0001255826,0.0001683678,0.0002591235,0.0001393385,0.00009974696],"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":[0.0002686209,0.0001493224,0.001210723,0.00016962,0.0001343819,0.000004166168,0.000314153,0.9918466,0.0005453001,0.0003564415,0.0003372686,0.004663379],"study_design_scores_gemma":[0.001921151,0.0006304944,0.0028888,0.0001625049,0.0002025809,0.00001988785,0.0008609492,0.9672795,0.006795772,0.0004939135,0.01809508,0.0006493473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09413403,0.0002095541,0.8969805,0.00005724402,0.004208611,0.001101717,0.002164137,0.001118354,0.00002581673],"genre_scores_gemma":[0.9967289,0.00001629039,0.0005966294,0.00003537795,0.0001169361,0.001338352,0.0009225979,0.00007536935,0.0001695771],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9025949,"threshold_uncertainty_score":0.9998692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0183763501461006,"score_gpt":0.2308425497579448,"score_spread":0.2124661996118442,"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."}}